{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/attention","entry":"Attention","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":344,"n_papers_ran":275,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":428,"n_samples_ran":334,"n_samples_fingerprinted":32,"n_places":428,"n_places_pointer_only":187,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":333,"unverified":94},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2608.07249","paper":"/paper/arxiv-2608-07249","title":"Stoicheia: Character-Level Masked Diffusion for Ancient Greek Textual Restoration, Parsing, and Metrical Scansion","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"ericu9500/stoicheia","path":"hf_release/modeling_char_bert_joint.py","file_url":"https://github.com/ericu9500/stoicheia/blob/HEAD/hf_release/modeling_char_bert_joint.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"084ae23049666bd7","mcp_get_code":{"code_sha256":"084ae23049666bd7"}},{"arxiv_id":"2607.12753","paper":"/paper/arxiv-2607-12753","title":"RFMSR: Residual Flow Matching for Image Super-Resolution","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"Faze-Hsw/RFMSR","path":"models/rfmsr.py","file_url":"https://github.com/Faze-Hsw/RFMSR/blob/HEAD/models/rfmsr.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf18d01a00853bcb","mcp_get_code":{"code_sha256":"cf18d01a00853bcb"}},{"arxiv_id":"2607.06611","paper":"/paper/arxiv-2607-06611","title":"Audio Sentiment Analysis via Distillation and Cross-Modal Integration of Generated Multilingual Transcripts","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"andreidurdun/cross-modal-audio-sentiment","path":"src/models/full_model.py","file_url":"https://github.com/andreidurdun/cross-modal-audio-sentiment/blob/HEAD/src/models/full_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7419d8ed5daa73c4","mcp_get_code":{"code_sha256":"7419d8ed5daa73c4"}},{"arxiv_id":"2606.27655","paper":"/paper/arxiv-2606-27655","title":"Temporal-Emerged Prompting for Segment Anything in Multiframe Infrared Small Target Detection","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"cdh8285/TEP-SAM","path":"models/sam_withToken.py","file_url":"https://github.com/cdh8285/TEP-SAM/blob/HEAD/models/sam_withToken.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d319af1582e25b7c","mcp_get_code":{"code_sha256":"d319af1582e25b7c"}},{"arxiv_id":"2606.21973","paper":"/paper/arxiv-2606-21973","title":"SPOTR: Spatio-temporal Pooling One-Token Reconstruction for Universal Physiological Signal Self-supervised Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"5GYYYYY/SPOTR","path":"SPOTR.py","file_url":"https://github.com/5GYYYYY/SPOTR/blob/HEAD/SPOTR.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"598e981b85828908","mcp_get_code":{"code_sha256":"598e981b85828908"}},{"arxiv_id":"2606.21973","paper":"/paper/arxiv-2606-21973","title":"SPOTR: Spatio-temporal Pooling One-Token Reconstruction for Universal Physiological Signal Self-supervised Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"PKUDigitalHealth/HeartLang","path":"modeling_pretrain.py","file_url":"https://github.com/PKUDigitalHealth/HeartLang/blob/HEAD/modeling_pretrain.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a79bbf16fe717d12","mcp_get_code":{"code_sha256":"a79bbf16fe717d12"}},{"arxiv_id":"2606.15207","paper":"/paper/arxiv-2606-15207","title":"Controlled Dynamics Attractor Transformer","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Angelov1vil/CDAT","path":"cdat-for-graph-classification/src/model/cdat.py","file_url":"https://github.com/Angelov1vil/CDAT/blob/HEAD/cdat-for-graph-classification/src/model/cdat.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f1404298354023e","mcp_get_code":{"code_sha256":"0f1404298354023e"}},{"arxiv_id":"2606.08414","paper":"/paper/arxiv-2606-08414","title":"PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"thu-ml/RDT2","path":"models/rdt/model.py","file_url":"https://github.com/thu-ml/RDT2/blob/HEAD/models/rdt/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b997b9a544314ad1","mcp_get_code":{"code_sha256":"b997b9a544314ad1"}},{"arxiv_id":"2606.05878","paper":"/paper/arxiv-2606-05878","title":"TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"EDF-Lab/ts-icl","path":"src/tsicl/model/network/ts_icl.py","file_url":"https://github.com/EDF-Lab/ts-icl/blob/HEAD/src/tsicl/model/network/ts_icl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e34e43271e61d5bb","mcp_get_code":{"code_sha256":"e34e43271e61d5bb"}},{"arxiv_id":"2605.31063","paper":"/paper/arxiv-2605-31063","title":"Free energy Estimation on Any State Space","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"J-zin/DNFS","path":"model.py","file_url":"https://github.com/J-zin/DNFS/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6ade5b78758c8379","mcp_get_code":{"code_sha256":"6ade5b78758c8379"}},{"arxiv_id":"2605.28166","paper":"/paper/arxiv-2605-28166","title":"QuITE: Query-Based Irregular Time Series Embedding","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Meaningfull9502/QuITE","path":"models/embeddings/quite.py","file_url":"https://github.com/Meaningfull9502/QuITE/blob/HEAD/models/embeddings/quite.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e512ff475844cfed","mcp_get_code":{"code_sha256":"e512ff475844cfed"}},{"arxiv_id":"2605.17811","paper":"/paper/arxiv-2605-17811","title":"One Model, Two Roles: Emergent Specialization in a Shared Recurrent Transformer","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"juchengshen/air","path":"models/air/air_1net_L2x_H2x_input_token_prepend.py","file_url":"https://github.com/juchengshen/air/blob/HEAD/models/air/air_1net_L2x_H2x_input_token_prepend.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e1fe279de6f03a37","mcp_get_code":{"code_sha256":"e1fe279de6f03a37"}},{"arxiv_id":"2605.07193","paper":"/paper/arxiv-2605-07193","title":"Coupling Models for One-Step Discrete Generation","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"pengzhangzhi/Coupling-Models","path":"mnist_guidance/coupling_model/transformer_flow.py","file_url":"https://github.com/pengzhangzhi/Coupling-Models/blob/HEAD/mnist_guidance/coupling_model/transformer_flow.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ee5882b3c65ffb8c","mcp_get_code":{"code_sha256":"ee5882b3c65ffb8c"}},{"arxiv_id":"2604.21473","paper":"/paper/arxiv-2604-21473","title":"Drug Synergy Prediction via Residual Graph Isomorphism Networks and Attention Mechanisms","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"szerq/ResGIN-att","path":"model.py","file_url":"https://github.com/szerq/ResGIN-att/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a4185facc81860c1","mcp_get_code":{"code_sha256":"a4185facc81860c1"}},{"arxiv_id":"2604.20041","paper":"/paper/arxiv-2604-20041","title":"Normalizing Flows with Iterative Denoising","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"apple/ml-itarflow","path":"transformer_flow.py","file_url":"https://github.com/apple/ml-itarflow/blob/HEAD/transformer_flow.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"7753ed9874d5cbbd","mcp_get_code":{"code_sha256":"7753ed9874d5cbbd"}},{"arxiv_id":"2604.15377","paper":"/paper/arxiv-2604-15377","title":"M3R: Localized Rainfall Nowcasting with Meteorology-Informed MultiModal Attention","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Sanjeev97/M3Rain","path":"models/m3.py","file_url":"https://github.com/Sanjeev97/M3Rain/blob/HEAD/models/m3.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"873c14050defdf6f","mcp_get_code":{"code_sha256":"873c14050defdf6f"}},{"arxiv_id":"2604.13307","paper":"/paper/arxiv-2604-13307","title":"Deep Spatially-Regularized and Superpixel-Based Diffusion Learning for Unsupervised Hyperspectral Image Clustering","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"vburan01/DS2DL","path":"pretrain_models.py","file_url":"https://github.com/vburan01/DS2DL/blob/HEAD/pretrain_models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"11fd4a23a9b8f490","mcp_get_code":{"code_sha256":"11fd4a23a9b8f490"}},{"arxiv_id":"2604.12518","paper":"/paper/arxiv-2604-12518","title":"Enhance-then-Balance Modality Collaboration for Robust Multimodal Sentiment Analysis","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"kangverse/EBMC","path":"EBMC/ebmc.py","file_url":"https://github.com/kangverse/EBMC/blob/HEAD/EBMC/ebmc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2bac95541907f2f5","mcp_get_code":{"code_sha256":"2bac95541907f2f5"}},{"arxiv_id":"2604.04420","paper":"/paper/arxiv-2604-04420","title":"Is Prompt Selection Necessary for Task-Free Online Continual Learning?","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"efficient-learning-lab/SinglePrompt","path":"models/singlePrompt.py","file_url":"https://github.com/efficient-learning-lab/SinglePrompt/blob/HEAD/models/singlePrompt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5fef41eb93946fd9","mcp_get_code":{"code_sha256":"5fef41eb93946fd9"}},{"arxiv_id":"2604.03203","paper":"/paper/arxiv-2604-03203","title":"PR3DICTR: A modular AI framework for medical 3D image-based detection and outcome prediction","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"DLinRadiotherapyUMCG/PR3DICTR","path":"src/models/TransRP_ViT.py","file_url":"https://github.com/DLinRadiotherapyUMCG/PR3DICTR/blob/HEAD/src/models/TransRP_ViT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7da1305c5860c375","mcp_get_code":{"code_sha256":"7da1305c5860c375"}},{"arxiv_id":"2603.18493","paper":"/paper/arxiv-2603-18493","title":"FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"jinotter3/FILT3R","path":"src/dust3r/model.py","file_url":"https://github.com/jinotter3/FILT3R/blob/HEAD/src/dust3r/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ab31579a725cd1e9","mcp_get_code":{"code_sha256":"ab31579a725cd1e9"}},{"arxiv_id":"2603.16739","paper":"/paper/arxiv-2603-16739","title":"SpecMoE: Spectral Mixture-of-Experts Foundation Model for Cross-Species EEG Decoding","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"935963004/LaBraM","path":"modeling_pretrain.py","file_url":"https://github.com/935963004/LaBraM/blob/HEAD/modeling_pretrain.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"68a5e3257881152d","mcp_get_code":{"code_sha256":"68a5e3257881152d"}},{"arxiv_id":"2603.14366","paper":"/paper/arxiv-2603-14366","title":"Representation Alignment for Just Image Transformers is not Easier than You Think","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"kaist-cvml/PixelREPA","path":"model_pixelREPA.py","file_url":"https://github.com/kaist-cvml/PixelREPA/blob/HEAD/model_pixelREPA.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6c7d7d14019a14d5","mcp_get_code":{"code_sha256":"6c7d7d14019a14d5"}},{"arxiv_id":"2603.11950","paper":"/paper/arxiv-2603-11950","title":"Learning Transferable Sensor Models via Language-Informed Pretraining","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"yuc0805/SLIP","path":"modeling_slip.py","file_url":"https://github.com/yuc0805/SLIP/blob/HEAD/modeling_slip.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a1f4664f7d4cbd00","mcp_get_code":{"code_sha256":"a1f4664f7d4cbd00"}},{"arxiv_id":"2603.00792","paper":"/paper/arxiv-2603-00792","title":"Neural Latent Arbitrary Lagrangian-Eulerian Grids for Fluid-Solid Interaction","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"therontau0054/Fisale","path":"model/fisale.py","file_url":"https://github.com/therontau0054/Fisale/blob/HEAD/model/fisale.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d17d8a42692307b4","mcp_get_code":{"code_sha256":"d17d8a42692307b4"}},{"arxiv_id":"2602.21043","paper":"/paper/arxiv-2602-21043","title":"T1: One-to-One Channel-Head Binding for Multivariate Time-Series Imputation","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Oppenheimerdinger/T1","path":"models/T1.py","file_url":"https://github.com/Oppenheimerdinger/T1/blob/HEAD/models/T1.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a32c89a2966be2db","mcp_get_code":{"code_sha256":"a32c89a2966be2db"}},{"arxiv_id":"2602.16951","paper":"/paper/arxiv-2602-16951","title":"BrainRVQ: A High-Fidelity EEG Foundation Model via Dual-Domain Residual Quantization and Hierarchical Autoregression","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"keqicmz/BrainRVQ","path":"DDRVQ/modeling_ddrvq.py","file_url":"https://github.com/keqicmz/BrainRVQ/blob/HEAD/DDRVQ/modeling_ddrvq.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b6ef437f49241781","mcp_get_code":{"code_sha256":"b6ef437f49241781"}},{"arxiv_id":"2602.14615","paper":"/paper/arxiv-2602-14615","title":"VariViT: A Vision Transformer for Variable Image Sizes","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Aswathi-Varma/varivit","path":"model/navit.py","file_url":"https://github.com/Aswathi-Varma/varivit/blob/HEAD/model/navit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"97cbaac807c38808","mcp_get_code":{"code_sha256":"97cbaac807c38808"}},{"arxiv_id":"2602.11281","paper":"/paper/arxiv-2602-11281","title":"DeepRed: an architecture for redshift estimation","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"1ArgoS1/PhotoZ","path":"models.py","file_url":"https://github.com/1ArgoS1/PhotoZ/blob/HEAD/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"44fbf9928a5d2215","mcp_get_code":{"code_sha256":"44fbf9928a5d2215"}},{"arxiv_id":"2602.04680","paper":"/paper/arxiv-2602-04680","title":"Audio ControlNet for Fine-Grained Audio Generation and Editing","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"haidog-yaqub/EzAudio","path":"src/models/controlnet.py","file_url":"https://github.com/haidog-yaqub/EzAudio/blob/HEAD/src/models/controlnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"531168589467d2a8","mcp_get_code":{"code_sha256":"531168589467d2a8"}},{"arxiv_id":"2602.03473","paper":"/paper/arxiv-2602-03473","title":"Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"LMMMEng/CaRE","path":"backbone/vit_brmoe.py","file_url":"https://github.com/LMMMEng/CaRE/blob/HEAD/backbone/vit_brmoe.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"52a9b5305ff1f5ef","mcp_get_code":{"code_sha256":"52a9b5305ff1f5ef"}},{"arxiv_id":"2602.02603","paper":"/paper/arxiv-2602-02603","title":"EchoJEPA: A Latent Predictive Foundation Model for Echocardiography","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"bowang-lab/EchoJEPA","path":"src/models/predictor.py","file_url":"https://github.com/bowang-lab/EchoJEPA/blob/HEAD/src/models/predictor.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3b523318502aa547","mcp_get_code":{"code_sha256":"3b523318502aa547"}},{"arxiv_id":"2602.02493","paper":"/paper/arxiv-2602-02493","title":"PixelGen: Improving Pixel Diffusion with Perceptual Supervision","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Zehong-Ma/PixelGen","path":"src/models/transformer/JiT.py","file_url":"https://github.com/Zehong-Ma/PixelGen/blob/HEAD/src/models/transformer/JiT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cfd8d30a6aecb8ba","mcp_get_code":{"code_sha256":"cfd8d30a6aecb8ba"}},{"arxiv_id":"2602.01951","paper":"/paper/arxiv-2602-01951","title":"Enabling Progressive Whole-slide Image Analysis with Multi-scale Pyramidal Network","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"AMLab-Amsterdam/AttentionDeepMIL","path":"model.py","file_url":"https://github.com/AMLab-Amsterdam/AttentionDeepMIL/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d4242c60b1f75593","mcp_get_code":{"code_sha256":"d4242c60b1f75593"}},{"arxiv_id":"2602.01951","paper":"/paper/arxiv-2602-01951","title":"Enabling Progressive Whole-slide Image Analysis with Multi-scale Pyramidal Network","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"hrlblab/CS-MIL","path":"Train_Test_Code/model3.py","file_url":"https://github.com/hrlblab/CS-MIL/blob/HEAD/Train_Test_Code/model3.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"54abaec4cabb8d79","mcp_get_code":{"code_sha256":"54abaec4cabb8d79"}},{"arxiv_id":"2601.22537","paper":"/paper/arxiv-2601-22537","title":"EndoCaver: Handling Fog, Blur and Glare in Endoscopic Images via Joint Deblurring-Segmentation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"ReaganWu/EndoCaver","path":"endocaver/model.py","file_url":"https://github.com/ReaganWu/EndoCaver/blob/HEAD/endocaver/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc0ece5f4524bef3","mcp_get_code":{"code_sha256":"bc0ece5f4524bef3"}},{"arxiv_id":"2601.17883","paper":"/paper/arxiv-2601-17883","title":"EEG-FM-Compass: Progress, Benchmarking, and Future Directions for EEG Foundation Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Dingkun0817/EEG-FM-Benchmark","path":"models/FM/EEGPT/Model_EEGPT.py","file_url":"https://github.com/Dingkun0817/EEG-FM-Benchmark/blob/HEAD/models/FM/EEGPT/Model_EEGPT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fb2c57145dd97d77","mcp_get_code":{"code_sha256":"fb2c57145dd97d77"}},{"arxiv_id":"2601.17271","paper":"/paper/arxiv-2601-17271","title":"Cross360: 360°Monocular Depth Estimation via Cross Projections Across Scales","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"huangkun101230/Cross360","path":"Networks/network.py","file_url":"https://github.com/huangkun101230/Cross360/blob/HEAD/Networks/network.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"268356f6c94c8799","mcp_get_code":{"code_sha256":"268356f6c94c8799"}},{"arxiv_id":"2601.12865","paper":"/paper/arxiv-2601-12865","title":"Proxy Robustness in Vision Language Models is Effortlessly Transferable","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"fxw13/HPT-GPD","path":"models/prompters.py","file_url":"https://github.com/fxw13/HPT-GPD/blob/HEAD/models/prompters.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"eafd21dd229fcdd2","mcp_get_code":{"code_sha256":"eafd21dd229fcdd2"}},{"arxiv_id":"2601.12530","paper":"/paper/arxiv-2601-12530","title":"XRefine: Attention-Guided Keypoint Match Refinement","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"boschresearch/xrefine","path":"model.py","file_url":"https://github.com/boschresearch/xrefine/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"9bc6940bb75b6d1d","mcp_get_code":{"code_sha256":"9bc6940bb75b6d1d"}},{"arxiv_id":"2601.03955","paper":"/paper/arxiv-2601-03955","title":"ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Kwai-Kolors/ResTok","path":"modeling/restok.py","file_url":"https://github.com/Kwai-Kolors/ResTok/blob/HEAD/modeling/restok.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"dc0b1a5e1598b3db","mcp_get_code":{"code_sha256":"dc0b1a5e1598b3db"}},{"arxiv_id":"2511.11090","paper":"/paper/arxiv-2511-11090","title":"A Space-Time Transformer for Precipitation Nowcasting","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"leharris3/satformer","path":"src/model/SaTformer/SaTformer.py","file_url":"https://github.com/leharris3/satformer/blob/HEAD/src/model/SaTformer/SaTformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"220675f054295e7d","mcp_get_code":{"code_sha256":"220675f054295e7d"}},{"arxiv_id":"2511.07222","paper":"/paper/arxiv-2511-07222","title":"Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"AIDC-AI/Omni-View","path":"modeling/bagel/bagel.py","file_url":"https://github.com/AIDC-AI/Omni-View/blob/HEAD/modeling/bagel/bagel.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f6284cebe0874960","mcp_get_code":{"code_sha256":"f6284cebe0874960"}},{"arxiv_id":"2510.16446","paper":"/paper/arxiv-2510-16446","title":"VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"iamjaekyun/vipamin","path":"src/models/vit_prompt/vit_exp_self.py","file_url":"https://github.com/iamjaekyun/vipamin/blob/HEAD/src/models/vit_prompt/vit_exp_self.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"321084c9cad68413","mcp_get_code":{"code_sha256":"321084c9cad68413"}},{"arxiv_id":"2510.09837","paper":"/paper/arxiv-2510-09837","title":"Domain Knowledge Infused Conditional Generative Models for Accelerating Drug Discovery","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"GenerativeDrugDiscovery/xImagand-DKI","path":"imagand.py","file_url":"https://github.com/GenerativeDrugDiscovery/xImagand-DKI/blob/HEAD/imagand.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"347e462bf844fd58","mcp_get_code":{"code_sha256":"347e462bf844fd58"}},{"arxiv_id":"2509.25033","paper":"/paper/arxiv-2509-25033","title":"VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"peacelwh/VT-FSL","path":"model/visformer.py","file_url":"https://github.com/peacelwh/VT-FSL/blob/HEAD/model/visformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1bd6240830af49b9","mcp_get_code":{"code_sha256":"1bd6240830af49b9"}},{"arxiv_id":"2509.24693","paper":"/paper/arxiv-2509-24693","title":"Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"hzlab/Brain-Harmony","path":"modules/harmonizer/stage1_pretrain/models.py","file_url":"https://github.com/hzlab/Brain-Harmony/blob/HEAD/modules/harmonizer/stage1_pretrain/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d3cc43506db5cff8","mcp_get_code":{"code_sha256":"d3cc43506db5cff8"}},{"arxiv_id":"2508.14588","paper":"/paper/arxiv-2508-14588","title":"Controllable Latent Space Augmentation for Digital Pathology","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"MICS-Lab/HistAug","path":"src/histaug/models/histaug_model.py","file_url":"https://github.com/MICS-Lab/HistAug/blob/HEAD/src/histaug/models/histaug_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC-BY-4.0","inline_ok":false,"code_sha256_prefix":"c6b04a03dabdc684","mcp_get_code":{"code_sha256":"c6b04a03dabdc684"}},{"arxiv_id":"2508.12787","paper":"/paper/arxiv-2508-12787","title":"Wavy Transformer","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"noguchisatoshi/Wavy-Transformer","path":"src/vit/wavy_vit.py","file_url":"https://github.com/noguchisatoshi/Wavy-Transformer/blob/HEAD/src/vit/wavy_vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8ad37341780ed312","mcp_get_code":{"code_sha256":"8ad37341780ed312"}},{"arxiv_id":"2508.03742","paper":"/paper/arxiv-2508-03742","title":"Boosting Vision Semantic Density with Anatomy Normality Modeling for Medical Vision-language Pre-training","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"alibaba-damo-academy/ViSD-Boost","path":"lavis/utils/model.py","file_url":"https://github.com/alibaba-damo-academy/ViSD-Boost/blob/HEAD/lavis/utils/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ed3aafb236b56fa3","mcp_get_code":{"code_sha256":"ed3aafb236b56fa3"}},{"arxiv_id":"2506.23151","paper":"/paper/memfof-high-resolution-training-for-memory","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","date":"2025-06-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"msu-video-group/memfof","path":"memfof/model.py","file_url":"https://github.com/msu-video-group/memfof/blob/HEAD/memfof/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"14f1b0e4c1e457ba","mcp_get_code":{"code_sha256":"14f1b0e4c1e457ba"}},{"arxiv_id":"2506.08887","paper":"/paper/discovla-discrepancy-reduction-in-vision-1","title":"DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval","date":"2025-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lunarshen/dsicovla","path":"tvr/models/module_GlobalCLS.py","file_url":"https://github.com/lunarshen/dsicovla/blob/HEAD/tvr/models/module_GlobalCLS.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4846155490b4fad9","mcp_get_code":{"code_sha256":"4846155490b4fad9"}},{"arxiv_id":"2506.05289","paper":"/paper/alitok-towards-sequence-modeling-alignment-1","title":"AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model","date":"2025-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ali-vilab/alitok","path":"modeling/alitok.py","file_url":"https://github.com/ali-vilab/alitok/blob/HEAD/modeling/alitok.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"90986cade2362a6c","mcp_get_code":{"code_sha256":"90986cade2362a6c"}},{"arxiv_id":"2505.23734","paper":"/paper/zpressor-bottleneck-aware-compression-for","title":"ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS","date":"2025-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziplab/ZPressor","path":"zpressor/zpressor.py","file_url":"https://github.com/ziplab/ZPressor/blob/HEAD/zpressor/zpressor.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cb661010ae406e86","mcp_get_code":{"code_sha256":"cb661010ae406e86"}},{"arxiv_id":"2505.22815","paper":"/paper/imts-is-worth-time-times-channel-patches","title":"IMTS is Worth Time $\\times$ Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction","date":"2025-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"whu-hzy/vimts","path":"IMTS/lib/models/visionts/models_mae.py","file_url":"https://github.com/whu-hzy/vimts/blob/HEAD/IMTS/lib/models/visionts/models_mae.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2698a4c6a1a414f9","mcp_get_code":{"code_sha256":"2698a4c6a1a414f9"}},{"arxiv_id":"2505.19813","paper":"/paper/golf-nrt-integrating-global-context-and-local","title":"GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis","date":"2025-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KLMAV-CUC/GoLF-NRT","path":"golf/model.py","file_url":"https://github.com/KLMAV-CUC/GoLF-NRT/blob/HEAD/golf/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6dc45d11eb542c0c","mcp_get_code":{"code_sha256":"6dc45d11eb542c0c"}},{"arxiv_id":"2505.19525","paper":"/paper/rethinking-gating-mechanism-in-sparse-moe","title":"Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate","date":"2025-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"icuraslw/official-repository-of-confsmoe","path":"models.py","file_url":"https://github.com/icuraslw/official-repository-of-confsmoe/blob/HEAD/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8cd46b9068cdd1b0","mcp_get_code":{"code_sha256":"8cd46b9068cdd1b0"}},{"arxiv_id":"2505.12630","paper":"/paper/degradation-aware-feature-perturbation-for","title":"Degradation-Aware Feature Perturbation for All-in-One Image Restoration","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TxpHome/DFPIR","path":"net/model.py","file_url":"https://github.com/TxpHome/DFPIR/blob/HEAD/net/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2df4621147879677","mcp_get_code":{"code_sha256":"2df4621147879677"}},{"arxiv_id":"2505.12628","paper":"/paper/dual-agent-reinforcement-learning-for","title":"Dual-Agent Reinforcement Learning for Automated Feature Generation","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"extess0/DARL","path":"feature_generation/embedding_policy.py","file_url":"https://github.com/extess0/DARL/blob/HEAD/feature_generation/embedding_policy.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5e0233489678853d","mcp_get_code":{"code_sha256":"5e0233489678853d"}},{"arxiv_id":"2505.12167","paper":"/paper/fable-a-localized-targeted-adversarial-attack","title":"FABLE: A Localized, Targeted Adversarial Attack on Weather Forecasting Models","date":"2025-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EDAPINENUT/CLCRN","path":"model/clcnn/recurrent/seq2seq_model.py","file_url":"https://github.com/EDAPINENUT/CLCRN/blob/HEAD/model/clcnn/recurrent/seq2seq_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7c7fe05cba3de422","mcp_get_code":{"code_sha256":"7c7fe05cba3de422"}},{"arxiv_id":"2505.02707","paper":"/paper/voila-voice-language-foundation-models-for","title":"Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play","date":"2025-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maitrix-org/Voila","path":"model.py","file_url":"https://github.com/maitrix-org/Voila/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7ef6c9efc12dc020","mcp_get_code":{"code_sha256":"7ef6c9efc12dc020"}},{"arxiv_id":"2504.16275","paper":"/paper/quantum-doubly-stochastic-transformers","title":"Quantum Doubly Stochastic Transformers","date":"2025-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"boschresearch/eurekaMoments","path":"vit.py","file_url":"https://github.com/boschresearch/eurekaMoments/blob/HEAD/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"27d7b9fb23e6948a","mcp_get_code":{"code_sha256":"27d7b9fb23e6948a"}},{"arxiv_id":"2504.13065","paper":"/paper/echoworld-learning-motion-aware-world-models","title":"EchoWorld: Learning Motion-Aware World Models for Echocardiography Probe Guidance","date":"2025-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LeapLabTHU/EchoWorld","path":"finetune/models/lvm_med.py","file_url":"https://github.com/LeapLabTHU/EchoWorld/blob/HEAD/finetune/models/lvm_med.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5934d853f37ea762","mcp_get_code":{"code_sha256":"5934d853f37ea762"}},{"arxiv_id":"2504.11295","paper":"/paper/autoregressive-distillation-of-diffusion","title":"Autoregressive Distillation of Diffusion Transformers","date":"2025-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alsdudrla10/ARD","path":"models_ARD.py","file_url":"https://github.com/alsdudrla10/ARD/blob/HEAD/models_ARD.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7013257ad549dfb6","mcp_get_code":{"code_sha256":"7013257ad549dfb6"}},{"arxiv_id":"2504.10746","paper":"/paper/hearing-anywhere-in-any-environment","title":"Hearing Anywhere in Any Environment","date":"2025-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DragonLiu1995/xRIR_code","path":"model/xRIR.py","file_url":"https://github.com/DragonLiu1995/xRIR_code/blob/HEAD/model/xRIR.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2780d8c996ac634c","mcp_get_code":{"code_sha256":"2780d8c996ac634c"}},{"arxiv_id":"2504.07963","paper":"/paper/pixelflow-pixel-space-generative-models-with","title":"PixelFlow: Pixel-Space Generative Models with Flow","date":"2025-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shoufachen/pixelflow","path":"pixelflow/model.py","file_url":"https://github.com/shoufachen/pixelflow/blob/HEAD/pixelflow/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"63693203a6480b29","mcp_get_code":{"code_sha256":"63693203a6480b29"}},{"arxiv_id":"2504.06504","paper":null,"title":"arXiv:2504.06504","date":null,"month_inferred_from_arxiv_id":"2025-04","title_source":null,"repo":"XiaohangYang829/STaR","path":"method/network.py","file_url":"https://github.com/XiaohangYang829/STaR/blob/HEAD/method/network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"45f149918d4149a3","mcp_get_code":{"code_sha256":"45f149918d4149a3"}},{"arxiv_id":"2504.03587","paper":"/paper/autossvh-exploring-automated-frame-sampling","title":"AutoSSVH: Exploring Automated Frame Sampling for Efficient Self-Supervised Video Hashing","date":"2025-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EliSpectre/CVPR25-AutoSSVH","path":"model/AutoSSVH.py","file_url":"https://github.com/EliSpectre/CVPR25-AutoSSVH/blob/HEAD/model/AutoSSVH.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e6117615a833f3b6","mcp_get_code":{"code_sha256":"e6117615a833f3b6"}},{"arxiv_id":"2503.20174","paper":"/paper/devil-is-in-the-uniformity-exploring-diverse","title":"Devil is in the Uniformity: Exploring Diverse Learners within Transformer for Image Restoration","date":"2025-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joshyZhou/HINT","path":"basicsr/models/archs/HINT_arch.py","file_url":"https://github.com/joshyZhou/HINT/blob/HEAD/basicsr/models/archs/HINT_arch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c5a0abf39590344f","mcp_get_code":{"code_sha256":"c5a0abf39590344f"}},{"arxiv_id":"2503.19331","paper":"/paper/cha-maevit-unifying-channel-aware-masked","title":"ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision Transformers for Improved Cross-Channel Learning","date":"2025-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chaudatascience/cha_mae_vit","path":"models/cha_mae_vit.py","file_url":"https://github.com/chaudatascience/cha_mae_vit/blob/HEAD/models/cha_mae_vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f52cc7c3cf1e75b2","mcp_get_code":{"code_sha256":"f52cc7c3cf1e75b2"}},{"arxiv_id":"2503.18211","paper":"/paper/simmotionedit-text-based-human-motion-editing","title":"SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction","date":"2025-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lzhyu/SimMotionEdit","path":"src/model/DiT_denoiser.py","file_url":"https://github.com/lzhyu/SimMotionEdit/blob/HEAD/src/model/DiT_denoiser.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"72ebe95ffd10e9f6","mcp_get_code":{"code_sha256":"72ebe95ffd10e9f6"}},{"arxiv_id":"2503.16997","paper":"/paper/steady-progress-beats-stagnation-mutual-aid","title":"Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation","date":"2025-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MQinghe/SynFoC","path":"code/sam_lora_image_encoder.py","file_url":"https://github.com/MQinghe/SynFoC/blob/HEAD/code/sam_lora_image_encoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b69ebb18cb6ce235","mcp_get_code":{"code_sha256":"b69ebb18cb6ce235"}},{"arxiv_id":"2503.10696","paper":"/paper/neighboring-autoregressive-modeling-for","title":"Neighboring Autoregressive Modeling for Efficient Visual Generation","date":"2025-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thisisbillhe/nar","path":"NAR-images/autoregressive/models/gpt.py","file_url":"https://github.com/thisisbillhe/nar/blob/HEAD/NAR-images/autoregressive/models/gpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"653880a319e2a083","mcp_get_code":{"code_sha256":"653880a319e2a083"}},{"arxiv_id":"2503.10252","paper":"/paper/svip-semantically-contextualized-visual","title":"SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning","date":"2025-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uqzhichen/SVIP","path":"models/vit_model.py","file_url":"https://github.com/uqzhichen/SVIP/blob/HEAD/models/vit_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f2eb5d6d927132b7","mcp_get_code":{"code_sha256":"f2eb5d6d927132b7"}},{"arxiv_id":"2503.06683","paper":"/paper/dynamic-dictionary-learning-for-remote","title":"Dynamic Dictionary Learning for Remote Sensing Image Segmentation","date":"2025-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XavierJiezou/D2LS","path":"network/models/d2ls.py","file_url":"https://github.com/XavierJiezou/D2LS/blob/HEAD/network/models/d2ls.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e843618eb9a8862f","mcp_get_code":{"code_sha256":"e843618eb9a8862f"}},{"arxiv_id":"2502.19854","paper":"/paper/one-model-for-all-low-level-task-interaction","title":"One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion","date":"2025-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AWCXV/GIFNet","path":"GIFNet_model.py","file_url":"https://github.com/AWCXV/GIFNet/blob/HEAD/GIFNet_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4c15b775fd5d8f13","mcp_get_code":{"code_sha256":"4c15b775fd5d8f13"}},{"arxiv_id":"2502.08958","paper":"/paper/biologically-plausible-brain-graph","title":"Biologically Plausible Brain Graph Transformer","date":"2025-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pcyyyy/BioBGT","path":"Model/models.py","file_url":"https://github.com/pcyyyy/BioBGT/blob/HEAD/Model/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"23dd64f2f6e8740e","mcp_get_code":{"code_sha256":"23dd64f2f6e8740e"}},{"arxiv_id":"2502.02257","paper":"/paper/unip-rethinking-pre-trained-attention","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","date":"2025-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"casiatao/unip","path":"UNIP_pretraining/models_unip.py","file_url":"https://github.com/casiatao/unip/blob/HEAD/UNIP_pretraining/models_unip.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"62f8d24046ec4b54","mcp_get_code":{"code_sha256":"62f8d24046ec4b54"}},{"arxiv_id":"2501.18936","paper":"/paper/adaptive-prompt-unlocking-the-power-of-visual","title":"Adaptive Prompt: Unlocking the Power of Visual Prompt Tuning","date":"2025-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Minhchuyentoancbn/VAPT","path":"src/models/vit_prompt/vit.py","file_url":"https://github.com/Minhchuyentoancbn/VAPT/blob/HEAD/src/models/vit_prompt/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"0dd334991598ccbc","mcp_get_code":{"code_sha256":"0dd334991598ccbc"}},{"arxiv_id":"2501.13420","paper":"/paper/lvface-large-vision-model-for-face-recogniton","title":"LVFace: Large Vision model for Face Recogniton","date":"2025-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/LVFace","path":"backbones/vit.py","file_url":"https://github.com/bytedance/LVFace/blob/HEAD/backbones/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"70e772c3db465e9e","mcp_get_code":{"code_sha256":"70e772c3db465e9e"}},{"arxiv_id":"2501.08303","paper":"/paper/advancing-semantic-future-prediction-through","title":"Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers","date":"2025-01-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sta8is/futurist","path":"src/futurist.py","file_url":"https://github.com/sta8is/futurist/blob/HEAD/src/futurist.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f7968fce35e007d8","mcp_get_code":{"code_sha256":"f7968fce35e007d8"}},{"arxiv_id":"2501.07256","paper":"/paper/edgetam-on-device-track-anything-model","title":"EdgeTAM: On-Device Track Anything Model","date":"2025-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/sam2","path":"sam2/modeling/memory_attention.py","file_url":"https://github.com/facebookresearch/sam2/blob/HEAD/sam2/modeling/memory_attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c140570681a00c3c","mcp_get_code":{"code_sha256":"c140570681a00c3c"}},{"arxiv_id":"2501.00880","paper":"/paper/improving-autoregressive-visual-generation","title":"Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction","date":"2025-01-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sjtuplayer/IAR","path":"autoregressive/models/gpt.py","file_url":"https://github.com/sjtuplayer/IAR/blob/HEAD/autoregressive/models/gpt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6f2102734f185e9f","mcp_get_code":{"code_sha256":"6f2102734f185e9f"}},{"arxiv_id":"2412.20803","paper":"/paper/frequency-aware-event-cloud-network","title":"Frequency-aware Event Cloud Network","date":"2024-12-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rhwxmx/SECNet_ICML","path":"models/FECNet.py","file_url":"https://github.com/rhwxmx/SECNet_ICML/blob/HEAD/models/FECNet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c9ee9d4e2695ce82","mcp_get_code":{"code_sha256":"c9ee9d4e2695ce82"}},{"arxiv_id":"2412.14803","paper":"/paper/video-prediction-policy-a-generalist-robot","title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","date":"2024-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"roboterax/video-prediction-policy","path":"policy_models/module/Video_Former.py","file_url":"https://github.com/roboterax/video-prediction-policy/blob/HEAD/policy_models/module/Video_Former.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8e4a59472aae19a1","mcp_get_code":{"code_sha256":"8e4a59472aae19a1"}},{"arxiv_id":"2412.14169","paper":"/paper/autoregressive-video-generation-without","title":"Autoregressive Video Generation without Vector Quantization","date":"2024-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baaivision/nova","path":"diffnext/models/transformers/transformer_nova.py","file_url":"https://github.com/baaivision/nova/blob/HEAD/diffnext/models/transformers/transformer_nova.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d627a66e082b5f70","mcp_get_code":{"code_sha256":"d627a66e082b5f70"}},{"arxiv_id":"2412.06028","paper":"/paper/flexdit-dynamic-token-density-control-for","title":"FlexDiT: Dynamic Token Density Control for Diffusion Transformer","date":"2024-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"changsn/FlexDiT","path":"models.py","file_url":"https://github.com/changsn/FlexDiT/blob/HEAD/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"902271093e80c4ae","mcp_get_code":{"code_sha256":"902271093e80c4ae"}},{"arxiv_id":"2412.04786","paper":"/paper/slicing-vision-transformer-for-flexible","title":"Slicing Vision Transformer for Flexible Inference","date":"2024-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BeSpontaneous/Scala-pytorch","path":"models_scala.py","file_url":"https://github.com/BeSpontaneous/Scala-pytorch/blob/HEAD/models_scala.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7a9dd4ed0208fd2f","mcp_get_code":{"code_sha256":"7a9dd4ed0208fd2f"}},{"arxiv_id":"2411.09702","paper":"/paper/on-the-surprising-effectiveness-of-attention","title":"On the Surprising Effectiveness of Attention Transfer for Vision Transformers","date":"2024-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alexlioralexli/attention-transfer","path":"models_dual_vit.py","file_url":"https://github.com/alexlioralexli/attention-transfer/blob/HEAD/models_dual_vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"66fae84cdc8d8912","mcp_get_code":{"code_sha256":"66fae84cdc8d8912"}},{"arxiv_id":"2411.03859","paper":"/paper/unitraj-universal-human-trajectory-modeling","title":"UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces","date":"2024-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yasoz/UniTraj","path":"utils/unitraj.py","file_url":"https://github.com/Yasoz/UniTraj/blob/HEAD/utils/unitraj.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"acc6f4c1919828fe","mcp_get_code":{"code_sha256":"acc6f4c1919828fe"}},{"arxiv_id":"2411.02175","paper":"/paper/safe-slow-and-fast-parameter-efficient-tuning","title":"SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models","date":"2024-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MIFA-Lab/SAFE","path":"petl/vision_transformer_adapter.py","file_url":"https://github.com/MIFA-Lab/SAFE/blob/HEAD/petl/vision_transformer_adapter.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"78278c42c6ca5ca1","mcp_get_code":{"code_sha256":"78278c42c6ca5ca1"}},{"arxiv_id":"2410.21265","paper":"/paper/modular-duality-in-deep-learning","title":"Modular Duality in Deep Learning","date":"2024-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jxbz/modula","path":"modula/compound.py","file_url":"https://github.com/jxbz/modula/blob/HEAD/modula/compound.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d84cb4d5e50d1478","mcp_get_code":{"code_sha256":"d84cb4d5e50d1478"}},{"arxiv_id":"2410.11842","paper":"/paper/moh-multi-head-attention-as-mixture-of-head","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","date":"2024-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"skyworkai/moe-plus-plus","path":"MoE++/modeling_moe_plus_plus.py","file_url":"https://github.com/skyworkai/moe-plus-plus/blob/HEAD/MoE%2B%2B/modeling_moe_plus_plus.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"513d27b0995b5f3e","mcp_get_code":{"code_sha256":"513d27b0995b5f3e"}},{"arxiv_id":"2410.11842","paper":"/paper/moh-multi-head-attention-as-mixture-of-head","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","date":"2024-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"skyworkai/moh","path":"MoH-ViT/attention.py","file_url":"https://github.com/skyworkai/moh/blob/HEAD/MoH-ViT/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7b9f5a8e366cc24e","mcp_get_code":{"code_sha256":"7b9f5a8e366cc24e"}},{"arxiv_id":"2410.10356","paper":"/paper/fasterdit-towards-faster-diffusion","title":"FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hustvl/LightningDiT","path":"models/lightningdit.py","file_url":"https://github.com/hustvl/LightningDiT/blob/HEAD/models/lightningdit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"10d58a623eb5beb1","mcp_get_code":{"code_sha256":"10d58a623eb5beb1"}},{"arxiv_id":"2410.09633","paper":"/paper/duodiff-accelerating-diffusion-models-with-a","title":"DuoDiff: Accelerating Diffusion Models with a Dual-Backbone Approach","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"razvanmatisan/duodiff","path":"models/early_exit.py","file_url":"https://github.com/razvanmatisan/duodiff/blob/HEAD/models/early_exit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f9763b6132534e57","mcp_get_code":{"code_sha256":"f9763b6132534e57"}},{"arxiv_id":"2410.05711","paper":"/paper/diffusion-auto-regressive-transformer-for","title":"Diffusion Auto-regressive Transformer for Effective Self-supervised Time Series Forecasting","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingyue-cheng/timemae","path":"model/TimeMAE.py","file_url":"https://github.com/mingyue-cheng/timemae/blob/HEAD/model/TimeMAE.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3e37f2ef318e5fa9","mcp_get_code":{"code_sha256":"3e37f2ef318e5fa9"}},{"arxiv_id":"2410.02705","paper":"/paper/controlar-controllable-image-generation-with","title":"ControlAR: Controllable Image Generation with Autoregressive Models","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hustvl/controlar","path":"autoregressive/models/gpt.py","file_url":"https://github.com/hustvl/controlar/blob/HEAD/autoregressive/models/gpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8320019fce428945","mcp_get_code":{"code_sha256":"8320019fce428945"}},{"arxiv_id":"2410.00320","paper":"/paper/pointad-comprehending-3d-anomalies-from","title":"PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection","date":"2024-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zqhang/pointad","path":"AnomalyCLIP_lib/AnomalyCLIP.py","file_url":"https://github.com/zqhang/pointad/blob/HEAD/AnomalyCLIP_lib/AnomalyCLIP.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2e7ee770aa7c6018","mcp_get_code":{"code_sha256":"2e7ee770aa7c6018"}},{"arxiv_id":"2409.20012","paper":"/paper/towards-robust-multimodal-sentiment-analysis","title":"Towards Robust Multimodal Sentiment Analysis with Incomplete Data","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoyu-ha/lnln","path":"models/lnln.py","file_url":"https://github.com/haoyu-ha/lnln/blob/HEAD/models/lnln.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8ced8002b277acce","mcp_get_code":{"code_sha256":"8ced8002b277acce"}},{"arxiv_id":"2409.11401","paper":"/paper/teaching-dark-matter-simulations-to-speak-the","title":"Teaching dark matter simulations to speak the halo language","date":null,"month_inferred_from_arxiv_id":"2024-09","title_source":"archive","repo":"shivampcosmo/gotham","path":"src/model_enc_dec.py","file_url":"https://github.com/shivampcosmo/gotham/blob/HEAD/src/model_enc_dec.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"35d8699d51065828","mcp_get_code":{"code_sha256":"35d8699d51065828"}},{"arxiv_id":"2409.10473","paper":"/paper/macdiff-unified-skeleton-modeling-with-masked","title":"MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion","date":"2024-09-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LehongWu/MacDiff","path":"model/transformer_macdiff.py","file_url":"https://github.com/LehongWu/MacDiff/blob/HEAD/model/transformer_macdiff.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c41cf977fcc5f5cb","mcp_get_code":{"code_sha256":"c41cf977fcc5f5cb"}},{"arxiv_id":"2409.09016","paper":"/paper/closed-loop-visuomotor-control-with","title":"Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation","date":null,"month_inferred_from_arxiv_id":"2024-09","title_source":"archive","repo":"OpenDriveLab/CLOVER","path":"FeedbackPolicy/models/policy.py","file_url":"https://github.com/OpenDriveLab/CLOVER/blob/HEAD/FeedbackPolicy/models/policy.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"08c3841b48475b05","mcp_get_code":{"code_sha256":"08c3841b48475b05"}},{"arxiv_id":"2409.01156","paper":"/paper/tempme-video-temporal-token-merging-for","title":"TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval","date":"2024-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LunarShen/TempMe","path":"tvr/models/module_tome_patch.py","file_url":"https://github.com/LunarShen/TempMe/blob/HEAD/tvr/models/module_tome_patch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cbfdf39eacd6be6c","mcp_get_code":{"code_sha256":"cbfdf39eacd6be6c"}},{"arxiv_id":"2408.14916","paper":"/paper/towards-real-world-event-guided-low-light","title":"Towards Real-world Event-guided Low-light Video Enhancement and Deblurring","date":"2024-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"intelpro/ELEDNet","path":"models/model_factory/models_final.py","file_url":"https://github.com/intelpro/ELEDNet/blob/HEAD/models/model_factory/models_final.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"26e8253d2d530c87","mcp_get_code":{"code_sha256":"26e8253d2d530c87"}},{"arxiv_id":"2408.14080","paper":"/paper/sonics-synthetic-or-not-identifying","title":"SONICS: Synthetic Or Not -- Identifying Counterfeit Songs","date":"2024-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"awsaf49/sonics","path":"sonics/models/spectttra.py","file_url":"https://github.com/awsaf49/sonics/blob/HEAD/sonics/models/spectttra.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"c3ac8c3472cc1f67","mcp_get_code":{"code_sha256":"c3ac8c3472cc1f67"}},{"arxiv_id":"2408.00714","paper":"/paper/2408-00714","title":"SAM 2: Segment Anything in Images and Videos","date":"2024-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"idea-research/grounded-sam-2","path":"sam2/modeling/sam2_base.py","file_url":"https://github.com/idea-research/grounded-sam-2/blob/HEAD/sam2/modeling/sam2_base.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d47d7ea80c6eb2e1","mcp_get_code":{"code_sha256":"d47d7ea80c6eb2e1"}},{"arxiv_id":"2408.00714","paper":"/paper/2408-00714","title":"SAM 2: Segment Anything in Images and Videos","date":"2024-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/sam2","path":"sam2/modeling/sam2_base.py","file_url":"https://github.com/facebookresearch/sam2/blob/HEAD/sam2/modeling/sam2_base.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d505eb599e148d6a","mcp_get_code":{"code_sha256":"d505eb599e148d6a"}},{"arxiv_id":"2407.16448","paper":"/paper/monowad-weather-adaptive-diffusion-model-for","title":"MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection","date":"2024-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VisualAIKHU/MonoWAD","path":"visualDet3D/networks/detectors/MonoWAD.py","file_url":"https://github.com/VisualAIKHU/MonoWAD/blob/HEAD/visualDet3D/networks/detectors/MonoWAD.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dfac04afda97fe38","mcp_get_code":{"code_sha256":"dfac04afda97fe38"}},{"arxiv_id":"2407.16171","paper":"/paper/learning-trimodal-relation-for-avqa-with","title":"Learning Trimodal Relation for AVQA with Missing Modality","date":"2024-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VisualAIKHU/Missing-AVQA","path":"net_grd_avst/net_avst.py","file_url":"https://github.com/VisualAIKHU/Missing-AVQA/blob/HEAD/net_grd_avst/net_avst.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"100973e0dc95d746","mcp_get_code":{"code_sha256":"100973e0dc95d746"}},{"arxiv_id":"2407.15837","paper":"/paper/towards-latent-masked-image-modeling-for-self","title":"Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learning","date":"2024-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yibingwei-1/LatentMIM","path":"models_lmim.py","file_url":"https://github.com/yibingwei-1/LatentMIM/blob/HEAD/models_lmim.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"97fb93bd98cfce58","mcp_get_code":{"code_sha256":"97fb93bd98cfce58"}},{"arxiv_id":"2407.13987","paper":"/paper/realviformer-investigating-attention-for-real","title":"RealViformer: Investigating Attention for Real-World Video Super-Resolution","date":"2024-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yuehan717/RealViformer","path":"archs/realviformer_arch.py","file_url":"https://github.com/Yuehan717/RealViformer/blob/HEAD/archs/realviformer_arch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c673f82c27d694b0","mcp_get_code":{"code_sha256":"c673f82c27d694b0"}},{"arxiv_id":"2407.09523","paper":"/paper/musecl-predicting-urban-socioeconomic","title":"MuseCL: Predicting Urban Socioeconomic Indicators via Multi-Semantic Contrastive Learning","date":"2024-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xixianyong/musecl","path":"attentive-fusion/fusion_module.py","file_url":"https://github.com/xixianyong/musecl/blob/HEAD/attentive-fusion/fusion_module.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2fc4ffe95ff2e97b","mcp_get_code":{"code_sha256":"2fc4ffe95ff2e97b"}},{"arxiv_id":"2406.07879","paper":"/paper/kernelwarehouse-rethinking-the-design-of","title":"KernelWarehouse: Rethinking the Design of Dynamic Convolution","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"osvai/kernelwarehouse","path":"modules/kernel_warehouse.py","file_url":"https://github.com/osvai/kernelwarehouse/blob/HEAD/modules/kernel_warehouse.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"42f32503fc92ca6f","mcp_get_code":{"code_sha256":"42f32503fc92ca6f"}},{"arxiv_id":"2406.05629","paper":"/paper/separating-the-chirp-from-the-chat-self","title":"Separating the \"Chirp\" from the \"Chat\": Self-supervised Visual Grounding of Sound and Language","date":"2024-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mhamilton723/DenseAV","path":"denseav/aligners.py","file_url":"https://github.com/mhamilton723/DenseAV/blob/HEAD/denseav/aligners.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2e89b95f672076b0","mcp_get_code":{"code_sha256":"2e89b95f672076b0"}},{"arxiv_id":"2406.05478","paper":"/paper/revisiting-non-autoregressive-transformers","title":"Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis","date":"2024-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LeapLabTHU/ImprovedNAT","path":"libs/nat_model.py","file_url":"https://github.com/LeapLabTHU/ImprovedNAT/blob/HEAD/libs/nat_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c707cacd32c81e73","mcp_get_code":{"code_sha256":"c707cacd32c81e73"}},{"arxiv_id":"2406.04329","paper":"/paper/simplified-and-generalized-masked-diffusion","title":"Simplified and Generalized Masked Diffusion for Discrete Data","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-deepmind/md4","path":"md4/models/diffusion/md4.py","file_url":"https://github.com/google-deepmind/md4/blob/HEAD/md4/models/diffusion/md4.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b5d57c4d33c17740","mcp_get_code":{"code_sha256":"b5d57c4d33c17740"}},{"arxiv_id":"2406.01210","paper":"/paper/geminifusion-efficient-pixel-wise-multimodal","title":"GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer","date":"2024-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiadingcn/geminifusion","path":"models/mix_transformer.py","file_url":"https://github.com/jiadingcn/geminifusion/blob/HEAD/models/mix_transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"19d28354dedaaeba","mcp_get_code":{"code_sha256":"19d28354dedaaeba"}},{"arxiv_id":"2405.20649","paper":"/paper/reward-based-input-construction-for-cross","title":"Reward-based Input Construction for Cross-document Relation Extraction","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aailabkaist/REIC","path":"ecrim-reic/main_reic.py","file_url":"https://github.com/aailabkaist/REIC/blob/HEAD/ecrim-reic/main_reic.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4ebd5c0e327383fa","mcp_get_code":{"code_sha256":"4ebd5c0e327383fa"}},{"arxiv_id":"2405.19783","paper":"/paper/instruction-guided-visual-masking","title":"Instruction-Guided Visual Masking","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"2toinf/ivm","path":"model/IVM.py","file_url":"https://github.com/2toinf/ivm/blob/HEAD/model/IVM.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b5bf903edd1dcafd","mcp_get_code":{"code_sha256":"b5bf903edd1dcafd"}},{"arxiv_id":"2405.16727","paper":"/paper/disentangling-and-integrating-relational-and","title":"Disentangling and Integrating Relational and Sensory Information in Transformer Architectures","date":"2024-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"awni00/abstract_transformer","path":"dual_attention_transformer.py","file_url":"https://github.com/awni00/abstract_transformer/blob/HEAD/dual_attention_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"437880805ab90b88","mcp_get_code":{"code_sha256":"437880805ab90b88"}},{"arxiv_id":"2405.16727","paper":"/paper/disentangling-and-integrating-relational-and","title":"Disentangling and Integrating Relational and Sensory Information in Transformer Architectures","date":"2024-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"awni00/dual-attention","path":"dual_attention/dual_attention.py","file_url":"https://github.com/awni00/dual-attention/blob/HEAD/dual_attention/dual_attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ed6c6aa45ef23326","mcp_get_code":{"code_sha256":"ed6c6aa45ef23326"}},{"arxiv_id":"2405.16419","paper":"/paper/enhancing-feature-diversity-boosts-channel","title":"Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers","date":"2024-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chaudatascience/diverse_channel_vit","path":"models/dichavit.py","file_url":"https://github.com/chaudatascience/diverse_channel_vit/blob/HEAD/models/dichavit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b02da06042eb84e7","mcp_get_code":{"code_sha256":"b02da06042eb84e7"}},{"arxiv_id":"2405.16005","paper":"/paper/ptq4dit-post-training-quantization-for","title":"PTQ4DiT: Post-training Quantization for Diffusion Transformers","date":"2024-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adreamwu/ptq4dit","path":"quant/layer_recon.py","file_url":"https://github.com/adreamwu/ptq4dit/blob/HEAD/quant/layer_recon.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"623291d109e82c34","mcp_get_code":{"code_sha256":"623291d109e82c34"}},{"arxiv_id":"2405.14791","paper":"/paper/recurrent-early-exits-for-federated-learning","title":"Recurrent Early Exits for Federated Learning with Heterogeneous Clients","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"royson/reefl","path":"src/models/reefl_vit.py","file_url":"https://github.com/royson/reefl/blob/HEAD/src/models/reefl_vit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dfbc1c3d50b97f50","mcp_get_code":{"code_sha256":"dfbc1c3d50b97f50"}},{"arxiv_id":"2405.13985","paper":"/paper/lookhere-vision-transformers-with-directed","title":"LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate","date":"2024-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"greencubic/lookhere","path":"lookhere.py","file_url":"https://github.com/greencubic/lookhere/blob/HEAD/lookhere.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b35e50a694a6b62e","mcp_get_code":{"code_sha256":"b35e50a694a6b62e"}},{"arxiv_id":"2405.13911","paper":"/paper/topa-extend-large-language-models-for-video","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","date":"2024-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dhg-wei/topa","path":"llama/model.py","file_url":"https://github.com/dhg-wei/topa/blob/HEAD/llama/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e4aee67fbc499c70","mcp_get_code":{"code_sha256":"e4aee67fbc499c70"}},{"arxiv_id":"2405.06312","paper":"/paper/fedgcs-a-generative-framework-for-efficient","title":"FedGCS: A Generative Framework for Efficient Client Selection in Federated Learning via Gradient-based Optimization","date":"2024-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhiyuan-ning/GenerativeFL","path":"autos/model.py","file_url":"https://github.com/zhiyuan-ning/GenerativeFL/blob/HEAD/autos/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e6ce9e1c9cf510ac","mcp_get_code":{"code_sha256":"e6ce9e1c9cf510ac"}},{"arxiv_id":"2405.03943","paper":"/paper/predictive-modeling-with-temporal-graphical","title":"Predictive Modeling with Temporal Graphical Representation on Electronic Health Records","date":"2024-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"The-Real-JerryChen/TRANS","path":"models/Seqmodels.py","file_url":"https://github.com/The-Real-JerryChen/TRANS/blob/HEAD/models/Seqmodels.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"890dae1cdee3d6a9","mcp_get_code":{"code_sha256":"890dae1cdee3d6a9"}},{"arxiv_id":"2405.01002","paper":"/paper/spider-a-unified-framework-for-context","title":"Spider: A Unified Framework for Context-dependent Concept Segmentation","date":"2024-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaoqi-zhao-dlut/spider-unicdseg","path":"model/DBS_group_prompt.py","file_url":"https://github.com/xiaoqi-zhao-dlut/spider-unicdseg/blob/HEAD/model/DBS_group_prompt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"68ed7eb275807bb1","mcp_get_code":{"code_sha256":"68ed7eb275807bb1"}},{"arxiv_id":"2404.15700","paper":"/paper/mas-sam-segment-any-marine-animal-with","title":"MAS-SAM: Segment Any Marine Animal with Aggregated Features","date":"2024-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Drchip61/MAS-SAM","path":"MAS-SAM/sam_lora_image_encoder.py","file_url":"https://github.com/Drchip61/MAS-SAM/blob/HEAD/MAS-SAM/sam_lora_image_encoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"83f765aaff985605","mcp_get_code":{"code_sha256":"83f765aaff985605"}},{"arxiv_id":"2404.12467","paper":"/paper/towards-multi-modal-transformers-in-federated","title":"Towards Multi-modal Transformers in Federated Learning","date":"2024-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"imguangyu/FedCola","path":"src/models/mome.py","file_url":"https://github.com/imguangyu/FedCola/blob/HEAD/src/models/mome.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b92c5b2c0953da52","mcp_get_code":{"code_sha256":"b92c5b2c0953da52"}},{"arxiv_id":"2404.04624","paper":"/paper/bridging-the-gap-between-end-to-end-and-two","title":"Bridging the Gap Between End-to-End and Two-Step Text Spotting","date":"2024-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mxin262/bridging-text-spotting","path":"adet/modeling/bridge.py","file_url":"https://github.com/mxin262/bridging-text-spotting/blob/HEAD/adet/modeling/bridge.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f07a7b5124daa4d3","mcp_get_code":{"code_sha256":"f07a7b5124daa4d3"}},{"arxiv_id":"2404.04624","paper":"/paper/bridging-the-gap-between-end-to-end-and-two","title":"Bridging the Gap Between End-to-End and Two-Step Text Spotting","date":"2024-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"husterpzh/pssr","path":"model.py","file_url":"https://github.com/husterpzh/pssr/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a55e20272adb06c8","mcp_get_code":{"code_sha256":"a55e20272adb06c8"}},{"arxiv_id":"2404.01547","paper":"/paper/bidirectional-multi-scale-implicit-neural","title":"Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cschenxiang/NeRD-Rain","path":"model.py","file_url":"https://github.com/cschenxiang/NeRD-Rain/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"df381277d7bba35a","mcp_get_code":{"code_sha256":"df381277d7bba35a"}},{"arxiv_id":"2404.01524","paper":"/paper/on-train-test-class-overlap-and-detection-for","title":"On Train-Test Class Overlap and Detection for Image Retrieval","date":"2024-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MCC-WH/Token","path":"networks/RetrievalNet.py","file_url":"https://github.com/MCC-WH/Token/blob/HEAD/networks/RetrievalNet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1703890780718a9f","mcp_get_code":{"code_sha256":"1703890780718a9f"}},{"arxiv_id":"2404.00288","paper":null,"title":"arXiv:2404.00288","date":null,"month_inferred_from_arxiv_id":"2024-04","title_source":null,"repo":"joshyZhou/FPro","path":"basicsr/models/archs/FPro_arch.py","file_url":"https://github.com/joshyZhou/FPro/blob/HEAD/basicsr/models/archs/FPro_arch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"93e865b611626ba4","mcp_get_code":{"code_sha256":"93e865b611626ba4"}},{"arxiv_id":"2403.19963","paper":"/paper/efficient-modulation-for-vision-networks","title":"Efficient Modulation for Vision Networks","date":"2024-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ma-xu/efficientmod","path":"models/EfficientMod.py","file_url":"https://github.com/ma-xu/efficientmod/blob/HEAD/models/EfficientMod.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"99bce211812fcf7a","mcp_get_code":{"code_sha256":"99bce211812fcf7a"}},{"arxiv_id":"2403.19638","paper":"/paper/siamese-vision-transformers-are-scalable","title":"Siamese Vision Transformers are Scalable Audio-visual Learners","date":"2024-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GenjiB/AVSiam","path":"src/models/cav_mae_base.py","file_url":"https://github.com/GenjiB/AVSiam/blob/HEAD/src/models/cav_mae_base.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ade838e8920e111","mcp_get_code":{"code_sha256":"7ade838e8920e111"}},{"arxiv_id":"2403.18548","paper":"/paper/a-semi-supervised-nighttime-dehazing-baseline","title":"A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint","date":"2024-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Xiaofeng-life/SFSNiD","path":"methods/MyNightDehazing/SFSNiD.py","file_url":"https://github.com/Xiaofeng-life/SFSNiD/blob/HEAD/methods/MyNightDehazing/SFSNiD.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3875f8f476e9b25a","mcp_get_code":{"code_sha256":"3875f8f476e9b25a"}},{"arxiv_id":"2403.18271","paper":"/paper/unleashing-the-potential-of-sam-for-medical","title":"Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding","date":"2024-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Cccccczh404/H-SAM","path":"segment_anything/modeling/mask_decoder_224.py","file_url":"https://github.com/Cccccczh404/H-SAM/blob/HEAD/segment_anything/modeling/mask_decoder_224.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"284d02bbefb07995","mcp_get_code":{"code_sha256":"284d02bbefb07995"}},{"arxiv_id":"2403.17749","paper":"/paper/multi-task-dense-prediction-via-mixture-of","title":"Multi-Task Dense Prediction via Mixture of Low-Rank Experts","date":"2024-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YuqiYang213/MLoRE","path":"models/transformers/MLoRE.py","file_url":"https://github.com/YuqiYang213/MLoRE/blob/HEAD/models/transformers/MLoRE.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9ac08340b51f89c7","mcp_get_code":{"code_sha256":"9ac08340b51f89c7"}},{"arxiv_id":"2403.15835","paper":"/paper/once-for-both-single-stage-of-importance-and","title":"Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression","date":"2024-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hankye/once-for-both","path":"models/layers.py","file_url":"https://github.com/hankye/once-for-both/blob/HEAD/models/layers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f2002139d1ca4bf4","mcp_get_code":{"code_sha256":"f2002139d1ca4bf4"}},{"arxiv_id":"2403.10254","paper":"/paper/magic-tokens-select-diverse-tokens-for-multi","title":"Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification","date":"2024-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"924973292/fusionreid","path":"modeling/fusion_part/fusion.py","file_url":"https://github.com/924973292/fusionreid/blob/HEAD/modeling/fusion_part/fusion.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4f2b5c4adcb39a83","mcp_get_code":{"code_sha256":"4f2b5c4adcb39a83"}},{"arxiv_id":"2403.08568","paper":"/paper/consistent-prompting-for-rehearsal-free","title":"Consistent Prompting for Rehearsal-Free Continual Learning","date":"2024-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Zhanxin-Gao/CPrompt","path":"models/cprompt.py","file_url":"https://github.com/Zhanxin-Gao/CPrompt/blob/HEAD/models/cprompt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b1240c5b5f4c7eb3","mcp_get_code":{"code_sha256":"b1240c5b5f4c7eb3"}},{"arxiv_id":"2403.08161","paper":"/paper/lafs-landmark-based-facial-self-supervised","title":"LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition","date":"2024-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"szlbiubiubiu/lafs_cvpr2024","path":"face_pre_pro/ViT_face.py","file_url":"https://github.com/szlbiubiubiu/lafs_cvpr2024/blob/HEAD/face_pre_pro/ViT_face.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5eb1f008cc961666","mcp_get_code":{"code_sha256":"5eb1f008cc961666"}},{"arxiv_id":"2403.06225","paper":"/paper/most-motion-style-transformer-between-diverse","title":"MoST: Motion Style Transformer between Diverse Action Contents","date":"2024-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Boeun-Kim/MoST","path":"model/networks.py","file_url":"https://github.com/Boeun-Kim/MoST/blob/HEAD/model/networks.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e13e7ac880e2b43b","mcp_get_code":{"code_sha256":"e13e7ac880e2b43b"}},{"arxiv_id":"2403.05406","paper":"/paper/considering-nonstationary-within-multivariate","title":"Considering Nonstationary within Multivariate Time Series with Variational Hierarchical Transformer for Forecasting","date":"2024-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"flare200020/HTV_Trans","path":"HTV-Trans/models.py","file_url":"https://github.com/flare200020/HTV_Trans/blob/HEAD/HTV-Trans/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d8b17088c30d7c1f","mcp_get_code":{"code_sha256":"d8b17088c30d7c1f"}},{"arxiv_id":"2403.04492","paper":"/paper/discriminative-sample-guided-and-parameter","title":"Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning","date":"2024-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rashindrie/DIPA","path":"models/vision_transformer_extended.py","file_url":"https://github.com/rashindrie/DIPA/blob/HEAD/models/vision_transformer_extended.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9d399688f8fea385","mcp_get_code":{"code_sha256":"9d399688f8fea385"}},{"arxiv_id":"2403.01412","paper":"/paper/lum-vit-learnable-under-sampling-mask-vision","title":"LUM-ViT: Learnable Under-sampling Mask Vision Transformer for Bandwidth Limited Optical Signal Acquisition","date":"2024-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maxllf/lum-vit","path":"LUM-ViT.py","file_url":"https://github.com/maxllf/lum-vit/blob/HEAD/LUM-ViT.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"71f6284d7ea766a7","mcp_get_code":{"code_sha256":"71f6284d7ea766a7"}},{"arxiv_id":"2403.00939","paper":"/paper/g3dr-generative-3d-reconstruction-in-imagenet","title":"G3DR: Generative 3D Reconstruction in ImageNet","date":"2024-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"preddy5/G3DR","path":"src/unet.py","file_url":"https://github.com/preddy5/G3DR/blob/HEAD/src/unet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aff8d7e511059536","mcp_get_code":{"code_sha256":"aff8d7e511059536"}},{"arxiv_id":"2402.17228","paper":"/paper/feature-re-embedding-towards-foundation-model","title":"Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DearCaat/RRT-MIL","path":"modules/rrt.py","file_url":"https://github.com/DearCaat/RRT-MIL/blob/HEAD/modules/rrt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"690f75057fc8497a","mcp_get_code":{"code_sha256":"690f75057fc8497a"}},{"arxiv_id":"2402.17228","paper":"/paper/feature-re-embedding-towards-foundation-model","title":"Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dearcaat/mhim-mil","path":"modules/rrt.py","file_url":"https://github.com/dearcaat/mhim-mil/blob/HEAD/modules/rrt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ce18178f893178a0","mcp_get_code":{"code_sha256":"ce18178f893178a0"}},{"arxiv_id":"2402.15160","paper":"/paper/spatially-aware-transformer-memory-for","title":"Spatially-Aware Transformer for Embodied Agents","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"junmokane/spatially-aware-transformer","path":"htm/hcam.py","file_url":"https://github.com/junmokane/spatially-aware-transformer/blob/HEAD/htm/hcam.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a6eea8936d08b19d","mcp_get_code":{"code_sha256":"a6eea8936d08b19d"}},{"arxiv_id":"2402.14905","paper":"/paper/mobilellm-optimizing-sub-billion-parameter","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jingyaogong/minimind","path":"model/model_minimind.py","file_url":"https://github.com/jingyaogong/minimind/blob/HEAD/model/model_minimind.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21b27f7007d54dbc","mcp_get_code":{"code_sha256":"21b27f7007d54dbc"}},{"arxiv_id":"2402.09450","paper":"/paper/guiding-masked-representation-learning-to","title":"Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bakqui/st-mem","path":"models/st_mem.py","file_url":"https://github.com/bakqui/st-mem/blob/HEAD/models/st_mem.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"99e49f8a77853d36","mcp_get_code":{"code_sha256":"99e49f8a77853d36"}},{"arxiv_id":"2402.09378","paper":"/paper/mobilespeech-a-fast-and-high-fidelity","title":"MobileSpeech: A Fast and High-Fidelity Framework for Mobile Zero-Shot Text-to-Speech","date":"2024-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"enhuiz/vall-e","path":"vall_e/vall_e/ar.py","file_url":"https://github.com/enhuiz/vall-e/blob/HEAD/vall_e/vall_e/ar.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8fe53745e4d5d22f","mcp_get_code":{"code_sha256":"8fe53745e4d5d22f"}},{"arxiv_id":"2402.08393","paper":"/paper/nfgtransformer-equivariant-representation","title":"NfgTransformer: Equivariant Representation Learning for Normal-form Games","date":null,"month_inferred_from_arxiv_id":"2024-02","title_source":"archive","repo":"google-deepmind/nfg_transformer","path":"nfg_transformer/network.py","file_url":"https://github.com/google-deepmind/nfg_transformer/blob/HEAD/nfg_transformer/network.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"98ce511a0e4fa8fa","mcp_get_code":{"code_sha256":"98ce511a0e4fa8fa"}},{"arxiv_id":"2402.07220","paper":"/paper/kvq-kaleidoscope-video-quality-assessment-for","title":"KVQ: Kwai Video Quality Assessment for Short-form Videos","date":"2024-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lixinustc/kvq-challenge-cvpr-ntire2024","path":"models/backbones/KSVQE_model.py","file_url":"https://github.com/lixinustc/kvq-challenge-cvpr-ntire2024/blob/HEAD/models/backbones/KSVQE_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4f17b32dad980e53","mcp_get_code":{"code_sha256":"4f17b32dad980e53"}},{"arxiv_id":"2402.05706","paper":"/paper/unified-speech-text-pretraining-for-spoken","title":"Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver-ai/usdm","path":"src/decoder/voicebox/model/voicebox.py","file_url":"https://github.com/naver-ai/usdm/blob/HEAD/src/decoder/voicebox/model/voicebox.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cd64f7d57cb575c2","mcp_get_code":{"code_sha256":"cd64f7d57cb575c2"}},{"arxiv_id":"2402.00033","paper":"/paper/lf-vit-reducing-spatial-redundancy-in-vision","title":"LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition","date":"2024-01-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"edgeai1/LF-ViT","path":"deit/models_deit.py","file_url":"https://github.com/edgeai1/LF-ViT/blob/HEAD/deit/models_deit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"52f85fff66a980a4","mcp_get_code":{"code_sha256":"52f85fff66a980a4"}},{"arxiv_id":"2401.15652","paper":"/paper/continuous-multiple-image-outpainting-in-one","title":"Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach","date":"2024-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sherrylone/pqdiff","path":"models/uvit.py","file_url":"https://github.com/sherrylone/pqdiff/blob/HEAD/models/uvit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c04864c0519e5926","mcp_get_code":{"code_sha256":"c04864c0519e5926"}},{"arxiv_id":"2401.08083","paper":"/paper/uv-sam-adapting-segment-anything-model-for","title":"UV-SAM: Adapting Segment Anything Model for Urban Village Identification","date":"2024-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tsinghua-fib-lab/uv-sam","path":"modules/sam/modeling/sam.py","file_url":"https://github.com/tsinghua-fib-lab/uv-sam/blob/HEAD/modules/sam/modeling/sam.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7bdac456c2af02c6","mcp_get_code":{"code_sha256":"7bdac456c2af02c6"}},{"arxiv_id":"2401.02937","paper":"/paper/locally-adaptive-neural-3d-morphable-models","title":"Locally Adaptive Neural 3D Morphable Models","date":"2024-01-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"michaeltrs/LAMM","path":"models/network.py","file_url":"https://github.com/michaeltrs/LAMM/blob/HEAD/models/network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9e5f32fddb005e9f","mcp_get_code":{"code_sha256":"9e5f32fddb005e9f"}},{"arxiv_id":"2401.00254","paper":"/paper/masked-image-modeling-via-dynamic-token","title":"Morphing Tokens Draw Strong Masked Image Models","date":"2023-12-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver-ai/dtm","path":"models/modeling_dtm.py","file_url":"https://github.com/naver-ai/dtm/blob/HEAD/models/modeling_dtm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"fb92f75afe01b0b3","mcp_get_code":{"code_sha256":"fb92f75afe01b0b3"}},{"arxiv_id":"2312.06647","paper":"/paper/4m-massively-multimodal-masked-modeling-1","title":"4M: Massively Multimodal Masked Modeling","date":"2023-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-4m","path":"fourm/models/fm.py","file_url":"https://github.com/apple/ml-4m/blob/HEAD/fourm/models/fm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"469d6eab97788ae3","mcp_get_code":{"code_sha256":"469d6eab97788ae3"}},{"arxiv_id":"2312.05284","paper":"/paper/0-1-data-makes-segment-anything-slim","title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","date":"2023-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"czg1225/slimsam","path":"prune_funcs.py","file_url":"https://github.com/czg1225/slimsam/blob/HEAD/prune_funcs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6e7d5271a0c585b0","mcp_get_code":{"code_sha256":"6e7d5271a0c585b0"}},{"arxiv_id":"2312.03701","paper":"/paper/self-conditioned-image-generation-via","title":"Return of Unconditional Generation: A Self-supervised Representation Generation Method","date":"2023-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LTH14/rcg","path":"pixel_generator/mage/models_mage.py","file_url":"https://github.com/LTH14/rcg/blob/HEAD/pixel_generator/mage/models_mage.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"33aedbcfd18d75e0","mcp_get_code":{"code_sha256":"33aedbcfd18d75e0"}},{"arxiv_id":"2311.18825","paper":"/paper/cast-cross-attention-in-space-and-time-for-1","title":"CAST: Cross-Attention in Space and Time for Video Action Recognition","date":"2023-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"khu-vll/cast","path":"models/bidir_modeling_crossattn.py","file_url":"https://github.com/khu-vll/cast/blob/HEAD/models/bidir_modeling_crossattn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"b181227b8cc95f3d","mcp_get_code":{"code_sha256":"b181227b8cc95f3d"}},{"arxiv_id":"2311.18433","paper":"/paper/e2pnet-event-to-point-cloud-registration-with-1","title":"E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning","date":"2023-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xmu-qcj/e2pnet","path":"EP2T/EP2T.py","file_url":"https://github.com/xmu-qcj/e2pnet/blob/HEAD/EP2T/EP2T.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2fbd100a3e967f1b","mcp_get_code":{"code_sha256":"2fbd100a3e967f1b"}},{"arxiv_id":"2311.05152","paper":"/paper/cross-modal-prompts-adapting-large-pre","title":"Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks","date":"2023-11-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoyi-duan/dg-sct","path":"DG-SCT/AVVP/nets/grouping.py","file_url":"https://github.com/haoyi-duan/dg-sct/blob/HEAD/DG-SCT/AVVP/nets/grouping.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c958e0e97761c999","mcp_get_code":{"code_sha256":"c958e0e97761c999"}},{"arxiv_id":"2311.00566","paper":"/paper/croma-remote-sensing-representations-with-1","title":"CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders","date":"2023-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"antofuller/croma","path":"pretrain_croma.py","file_url":"https://github.com/antofuller/croma/blob/HEAD/pretrain_croma.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1fcfdd6a3153b5d2","mcp_get_code":{"code_sha256":"1fcfdd6a3153b5d2"}},{"arxiv_id":"2310.15747","paper":"/paper/large-language-models-are-temporal-and-causal","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlvlab/Flipped-VQA","path":"llama/model.py","file_url":"https://github.com/mlvlab/Flipped-VQA/blob/HEAD/llama/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ea4fa90ff313cb77","mcp_get_code":{"code_sha256":"ea4fa90ff313cb77"}},{"arxiv_id":"2310.14017","paper":"/paper/contrast-everything-a-hierarchical","title":"Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series","date":"2023-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"emadeldeen24/TS-TCC","path":"models/TC.py","file_url":"https://github.com/emadeldeen24/TS-TCC/blob/HEAD/models/TC.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"617e0645b9972b67","mcp_get_code":{"code_sha256":"617e0645b9972b67"}},{"arxiv_id":"2310.13545","paper":"/paper/scalelong-towards-more-stable-training-of-1","title":"ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection","date":"2023-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/scalelong","path":"libs/uvit.py","file_url":"https://github.com/sail-sg/scalelong/blob/HEAD/libs/uvit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a21d05625a5f984b","mcp_get_code":{"code_sha256":"a21d05625a5f984b"}},{"arxiv_id":"2310.00093","paper":"/paper/datadam-efficient-dataset-distillation-with-1","title":"DataDAM: Efficient Dataset Distillation with Attention Matching","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"datadistillation/datadam","path":"main_DataDAM.py","file_url":"https://github.com/datadistillation/datadam/blob/HEAD/main_DataDAM.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4e14cbaa48d8cc75","mcp_get_code":{"code_sha256":"4e14cbaa48d8cc75"}},{"arxiv_id":"2309.16283","paper":"/paper/self-supervised-cross-view-representation-1","title":"Self-supervised Cross-view Representation Reconstruction for Change Captioning","date":"2023-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tuyunbin/SCORER","path":"models/SCORER.py","file_url":"https://github.com/tuyunbin/SCORER/blob/HEAD/models/SCORER.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"19702fabad2dd806","mcp_get_code":{"code_sha256":"19702fabad2dd806"}},{"arxiv_id":"2309.13524","paper":"/paper/global-correlated-3d-decoupling-transformer-1","title":"Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction","date":"2023-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"river-zhang/gta","path":"lib/net/Transformer.py","file_url":"https://github.com/river-zhang/gta/blob/HEAD/lib/net/Transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d47a4cbea53360d1","mcp_get_code":{"code_sha256":"d47a4cbea53360d1"}},{"arxiv_id":"2309.05927","paper":"/paper/frequency-aware-masked-autoencoders-for","title":"Frequency-Aware Masked Autoencoders for Multimodal Pretraining on Biosignals","date":"2023-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-famae","path":"bioFAME/models/algorithms.py","file_url":"https://github.com/apple/ml-famae/blob/HEAD/bioFAME/models/algorithms.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"42c8d64590336334","mcp_get_code":{"code_sha256":"42c8d64590336334"}},{"arxiv_id":"2309.02020","paper":"/paper/rawhdr-high-dynamic-range-image","title":"RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image","date":"2023-09-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jackzou233/RawHDR","path":"model.py","file_url":"https://github.com/jackzou233/RawHDR/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"29d50c0250eae7a9","mcp_get_code":{"code_sha256":"29d50c0250eae7a9"}},{"arxiv_id":"2308.15512","paper":"/paper/shatter-and-gather-learning-referring-image","title":"Shatter and Gather: Learning Referring Image Segmentation with Text Supervision","date":"2023-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kdwonn/SaG","path":"model/cross_modal_attention.py","file_url":"https://github.com/kdwonn/SaG/blob/HEAD/model/cross_modal_attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"12ea3b3517a96270","mcp_get_code":{"code_sha256":"12ea3b3517a96270"}},{"arxiv_id":"2308.14153","paper":"/paper/sparse-sampling-transformer-with-uncertainty","title":"Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks","date":"2023-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Ephemeral182/UDR-S2Former_deraining","path":"UDR_S2Former.py","file_url":"https://github.com/Ephemeral182/UDR-S2Former_deraining/blob/HEAD/UDR_S2Former.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e505e5b4c6c05324","mcp_get_code":{"code_sha256":"e505e5b4c6c05324"}},{"arxiv_id":"2308.14036","paper":"/paper/mb-taylorformer-multi-branch-efficient","title":"MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing","date":"2023-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FVL2020/ICCV-2023-MB-TaylorFormer","path":"basicsr/models/archs/MB_TaylorFormer.py","file_url":"https://github.com/FVL2020/ICCV-2023-MB-TaylorFormer/blob/HEAD/basicsr/models/archs/MB_TaylorFormer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"659261b010a72668","mcp_get_code":{"code_sha256":"659261b010a72668"}},{"arxiv_id":"2308.12216","paper":"/paper/sg-former-self-guided-transformer-with","title":"SG-Former: Self-guided Transformer with Evolving Token Reallocation","date":"2023-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OliverRensu/SG-Former","path":"sgformer.py","file_url":"https://github.com/OliverRensu/SG-Former/blob/HEAD/sgformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"62dc7968a3bc8849","mcp_get_code":{"code_sha256":"62dc7968a3bc8849"}},{"arxiv_id":"2308.10814","paper":"/paper/jumping-through-local-minima-quantization-in","title":"Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers","date":"2023-08-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"enyac-group/evol-q","path":"joint_evol_opt.py","file_url":"https://github.com/enyac-group/evol-q/blob/HEAD/joint_evol_opt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6ee85e42ebc1d6f2","mcp_get_code":{"code_sha256":"6ee85e42ebc1d6f2"}},{"arxiv_id":"2308.09951","paper":"/paper/semantics-meets-temporal-correspondence-self","title":"Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos","date":"2023-08-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shvdiwnkozbw/SMTC","path":"src/model/model_action.py","file_url":"https://github.com/shvdiwnkozbw/SMTC/blob/HEAD/src/model/model_action.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"59f6323575d06123","mcp_get_code":{"code_sha256":"59f6323575d06123"}},{"arxiv_id":"2308.04808","paper":"/paper/joint-relation-transformer-for-multi-person","title":"Joint-Relation Transformer for Multi-Person Motion Prediction","date":"2023-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MediaBrain-SJTU/JRTransformer","path":"model/model.py","file_url":"https://github.com/MediaBrain-SJTU/JRTransformer/blob/HEAD/model/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"94ca24363aab8053","mcp_get_code":{"code_sha256":"94ca24363aab8053"}},{"arxiv_id":"2308.04549","paper":"/paper/prune-spatio-temporal-tokens-by-semantic","title":"Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation","date":"2023-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Mark12Ding/STA","path":"model_vit.py","file_url":"https://github.com/Mark12Ding/STA/blob/HEAD/model_vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"a40d0b88efe57389","mcp_get_code":{"code_sha256":"a40d0b88efe57389"}},{"arxiv_id":"2307.15324","paper":"/paper/taskexpert-dynamically-assembling-multi-task","title":"TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts","date":"2023-07-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"prismformore/multi-task-transformer","path":"TaskPrompter/models/transformers/taskprompter.py","file_url":"https://github.com/prismformore/multi-task-transformer/blob/HEAD/TaskPrompter/models/transformers/taskprompter.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ee6bbe827f8d9472","mcp_get_code":{"code_sha256":"ee6bbe827f8d9472"}},{"arxiv_id":"2307.15254","paper":"/paper/multiple-instance-learning-framework-with","title":"Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification","date":"2023-07-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DearCaat/MHIM-MIL","path":"modules/mhim.py","file_url":"https://github.com/DearCaat/MHIM-MIL/blob/HEAD/modules/mhim.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cd5072f3dab80831","mcp_get_code":{"code_sha256":"cd5072f3dab80831"}},{"arxiv_id":"2307.09288","paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"glb400/Toy-RecLM","path":"model.py","file_url":"https://github.com/glb400/Toy-RecLM/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4334c46d3961b3fb","mcp_get_code":{"code_sha256":"4334c46d3961b3fb"}},{"arxiv_id":"2307.08579","paper":"/paper/scale-aware-modulation-meet-transformer","title":"Scale-Aware Modulation Meet Transformer","date":"2023-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AFeng-x/SMT","path":"models/smt.py","file_url":"https://github.com/AFeng-x/SMT/blob/HEAD/models/smt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f1fc650a5bc5f6c2","mcp_get_code":{"code_sha256":"f1fc650a5bc5f6c2"}},{"arxiv_id":"2306.13643","paper":"/paper/lightglue-local-feature-matching-at-light","title":"LightGlue: Local Feature Matching at Light Speed","date":"2023-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cvg/LightGlue","path":"lightglue/lightglue.py","file_url":"https://github.com/cvg/LightGlue/blob/HEAD/lightglue/lightglue.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a08f05b65312af52","mcp_get_code":{"code_sha256":"a08f05b65312af52"}},{"arxiv_id":"2306.05067","paper":"/paper/improving-visual-prompt-tuning-for-self","title":"Improving Visual Prompt Tuning for Self-supervised Vision Transformers","date":"2023-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ryongithub/gatedprompttuning","path":"src/models/vit_prompt/vit_mae.py","file_url":"https://github.com/ryongithub/gatedprompttuning/blob/HEAD/src/models/vit_prompt/vit_mae.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9d53ec26dfcd7416","mcp_get_code":{"code_sha256":"9d53ec26dfcd7416"}},{"arxiv_id":"2305.18446","paper":"/paper/trompt-towards-a-better-deep-neural-network","title":"Trompt: Towards a Better Deep Neural Network for Tabular Data","date":"2023-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LeoGrin/tabular-benchmark","path":"src/models/TabSurvey/models/tabtransformer.py","file_url":"https://github.com/LeoGrin/tabular-benchmark/blob/HEAD/src/models/TabSurvey/models/tabtransformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"40bd29725f53dbac","mcp_get_code":{"code_sha256":"40bd29725f53dbac"}},{"arxiv_id":"2305.16646","paper":"/paper/language-models-can-improve-event-prediction-1","title":"Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning","date":"2023-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ilampard/lamp","path":"models/ke_anhp/_model.py","file_url":"https://github.com/ilampard/lamp/blob/HEAD/models/ke_anhp/_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"71cbec2f001bc55b","mcp_get_code":{"code_sha256":"71cbec2f001bc55b"}},{"arxiv_id":"2305.13245","paper":"/paper/gqa-training-generalized-multi-query","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","date":"2023-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"knotgrass/attention","path":"attn/attention.py","file_url":"https://github.com/knotgrass/attention/blob/HEAD/attn/attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7bd4605898291f6a","mcp_get_code":{"code_sha256":"7bd4605898291f6a"}},{"arxiv_id":"2304.07193","paper":"/paper/dinov2-learning-robust-visual-features","title":"DINOv2: Learning Robust Visual Features without Supervision","date":"2023-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/highrescanopyheight","path":"models/backbone.py","file_url":"https://github.com/facebookresearch/highrescanopyheight/blob/HEAD/models/backbone.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8598c6b96e3a0fbb","mcp_get_code":{"code_sha256":"8598c6b96e3a0fbb"}},{"arxiv_id":"2304.07193","paper":"/paper/dinov2-learning-robust-visual-features","title":"DINOv2: Learning Robust Visual Features without Supervision","date":"2023-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ByungKwanLee/Causal-Unsupervised-Segmentation","path":"models/dinov2vit.py","file_url":"https://github.com/ByungKwanLee/Causal-Unsupervised-Segmentation/blob/HEAD/models/dinov2vit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9557b19d4ebe95ac","mcp_get_code":{"code_sha256":"9557b19d4ebe95ac"}},{"arxiv_id":"2304.05153","paper":"/paper/regression-based-deep-learning-predicts","title":"Regression-based Deep-Learning predicts molecular biomarkers from pathology slides","date":"2023-04-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"katherlab/marugoto","path":"marugoto/mil/model.py","file_url":"https://github.com/katherlab/marugoto/blob/HEAD/marugoto/mil/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc327f59a0424245","mcp_get_code":{"code_sha256":"bc327f59a0424245"}},{"arxiv_id":"2304.04952","paper":"/paper/data-efficient-image-quality-assessment-with","title":"Data-Efficient Image Quality Assessment with Attention-Panel Decoder","date":"2023-04-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"narthchin/DEIQT","path":"models/deiqt.py","file_url":"https://github.com/narthchin/DEIQT/blob/HEAD/models/deiqt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"389c0e1ba8cccd08","mcp_get_code":{"code_sha256":"389c0e1ba8cccd08"}},{"arxiv_id":"2304.03307","paper":"/paper/vita-clip-video-and-text-adaptive-clip-via","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","date":"2023-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TalalWasim/Vita-CLIP","path":"training/VitaCLIP_model.py","file_url":"https://github.com/TalalWasim/Vita-CLIP/blob/HEAD/training/VitaCLIP_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a56eadb4eb339fa4","mcp_get_code":{"code_sha256":"a56eadb4eb339fa4"}},{"arxiv_id":"2304.03283","paper":"/paper/diffusion-models-as-masked-autoencoders","title":"Diffusion Models as Masked Autoencoders","date":"2023-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kimdanni/DiffMAE","path":"models_cross.py","file_url":"https://github.com/kimdanni/DiffMAE/blob/HEAD/models_cross.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f7e0f3a36a14e867","mcp_get_code":{"code_sha256":"f7e0f3a36a14e867"}},{"arxiv_id":"2304.03195","paper":"/paper/micron-bert-bert-based-facial-micro","title":"Micron-BERT: BERT-based Facial Micro-Expression Recognition","date":"2023-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uark-cviu/Micron-BERT","path":"models/vision_transformer.py","file_url":"https://github.com/uark-cviu/Micron-BERT/blob/HEAD/models/vision_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8996bc39caa16502","mcp_get_code":{"code_sha256":"8996bc39caa16502"}},{"arxiv_id":"2303.17472","paper":"/paper/poseformerv2-exploring-frequency-domain-for","title":"PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation","date":"2023-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qitaozhao/poseformerv2","path":"mpi_inf_3dhp/model/model_poseformerv2.py","file_url":"https://github.com/qitaozhao/poseformerv2/blob/HEAD/mpi_inf_3dhp/model/model_poseformerv2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9af3eb132594e510","mcp_get_code":{"code_sha256":"9af3eb132594e510"}},{"arxiv_id":"2303.17152","paper":"/paper/mixed-autoencoder-for-self-supervised-visual","title":"Mixed Autoencoder for Self-supervised Visual Representation Learning","date":"2023-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Natyren/MixedAE","path":"mixedae/mixedae.py","file_url":"https://github.com/Natyren/MixedAE/blob/HEAD/mixedae/mixedae.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"adc42d841cf96a0a","mcp_get_code":{"code_sha256":"adc42d841cf96a0a"}},{"arxiv_id":"2303.17056","paper":"/paper/audio-visual-grouping-network-for-sound","title":"Audio-Visual Grouping Network for Sound Localization from Mixtures","date":"2023-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stonemo/avgn","path":"model.py","file_url":"https://github.com/stonemo/avgn/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"17d5ecc9fb88dc98","mcp_get_code":{"code_sha256":"17d5ecc9fb88dc98"}},{"arxiv_id":"2303.15555","paper":"/paper/object-discovery-from-motion-guided-tokens","title":"Object Discovery from Motion-Guided Tokens","date":"2023-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zpbao/MoTok","path":"models/model.py","file_url":"https://github.com/zpbao/MoTok/blob/HEAD/models/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fcfd6a91cff8bff5","mcp_get_code":{"code_sha256":"fcfd6a91cff8bff5"}},{"arxiv_id":"2303.14389","paper":"/paper/masked-diffusion-transformer-is-a-strong","title":"MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer","date":"2023-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/MDT","path":"masked_diffusion/models.py","file_url":"https://github.com/sail-sg/MDT/blob/HEAD/masked_diffusion/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"07d39f4cc0b2a473","mcp_get_code":{"code_sha256":"07d39f4cc0b2a473"}},{"arxiv_id":"2303.13755","paper":"/paper/sparsifiner-learning-sparse-instance","title":"Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers","date":"2023-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lim142857/Sparsifiner","path":"src/models/sparsifiner.py","file_url":"https://github.com/lim142857/Sparsifiner/blob/HEAD/src/models/sparsifiner.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cd7c6fd7feccfdc2","mcp_get_code":{"code_sha256":"cd7c6fd7feccfdc2"}},{"arxiv_id":"2303.12670","paper":"/paper/correlational-image-modeling-for-self","title":"Correlational Image Modeling for Self-Supervised Visual Pre-Training","date":"2023-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weivision/correlational-image-modeling","path":"models/cim.py","file_url":"https://github.com/weivision/correlational-image-modeling/blob/HEAD/models/cim.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e2796dfadcc960a6","mcp_get_code":{"code_sha256":"e2796dfadcc960a6"}},{"arxiv_id":"2303.11950","paper":"/paper/learning-a-sparse-transformer-network-for","title":"Learning A Sparse Transformer Network for Effective Image Deraining","date":"2023-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cschenxiang/drsformer","path":"basicsr/models/archs/DRSformer_arch.py","file_url":"https://github.com/cschenxiang/drsformer/blob/HEAD/basicsr/models/archs/DRSformer_arch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"50006ae54761f527","mcp_get_code":{"code_sha256":"50006ae54761f527"}},{"arxiv_id":"2303.10438","paper":"/paper/spatial-aware-token-for-weakly-supervised","title":"Spatial-Aware Token for Weakly Supervised Object Localization","date":"2023-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wpy1999/SAT","path":"Model/SAT.py","file_url":"https://github.com/wpy1999/SAT/blob/HEAD/Model/SAT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d3d6353eaf322103","mcp_get_code":{"code_sha256":"d3d6353eaf322103"}},{"arxiv_id":"2303.09859","paper":"/paper/trained-on-100-million-words-and-still-in","title":"Trained on 100 million words and still in shape: BERT meets British National Corpus","date":"2023-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ltgoslo/ltg-bert","path":"training/model.py","file_url":"https://github.com/ltgoslo/ltg-bert/blob/HEAD/training/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"7e10920e7b6674fc","mcp_get_code":{"code_sha256":"7e10920e7b6674fc"}},{"arxiv_id":"2303.09663","paper":"/paper/efficient-computation-sharing-for-multi-task","title":"Efficient Computation Sharing for Multi-Task Visual Scene Understanding","date":"2023-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sarashoouri/EfficientMTL","path":"Codes/multimae/multimae.py","file_url":"https://github.com/sarashoouri/EfficientMTL/blob/HEAD/Codes/multimae/multimae.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d969a5ba04920f2e","mcp_get_code":{"code_sha256":"d969a5ba04920f2e"}},{"arxiv_id":"2303.08685","paper":"/paper/making-vision-transformers-efficient-from-a","title":"Making Vision Transformers Efficient from A Token Sparsification View","date":"2023-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"changsn/STViT-R","path":"models/layers.py","file_url":"https://github.com/changsn/STViT-R/blob/HEAD/models/layers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"856fe98d76d7dd4b","mcp_get_code":{"code_sha256":"856fe98d76d7dd4b"}},{"arxiv_id":"2303.08340","paper":"/paper/videoflow-exploiting-temporal-cues-for-multi","title":"VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation","date":"2023-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XiaoyuShi97/VideoFlow","path":"core/Networks/MOFNetStack/network.py","file_url":"https://github.com/XiaoyuShi97/VideoFlow/blob/HEAD/core/Networks/MOFNetStack/network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9e99aacd9432009f","mcp_get_code":{"code_sha256":"9e99aacd9432009f"}},{"arxiv_id":"2303.08129","paper":"/paper/pimae-point-cloud-and-image-interactive","title":"PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection","date":"2023-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BLVLab/PiMAE","path":"Pretrain/models/pimae.py","file_url":"https://github.com/BLVLab/PiMAE/blob/HEAD/Pretrain/models/pimae.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1d16864030bea18b","mcp_get_code":{"code_sha256":"1d16864030bea18b"}},{"arxiv_id":"2303.06840","paper":"/paper/ddfm-denoising-diffusion-model-for-multi","title":"DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion","date":"2023-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaozixiang1228/if-film","path":"net/Film.py","file_url":"https://github.com/zhaozixiang1228/if-film/blob/HEAD/net/Film.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"98e962e3944f0fb6","mcp_get_code":{"code_sha256":"98e962e3944f0fb6"}},{"arxiv_id":"2303.06457","paper":"/paper/active-visual-exploration-based-on-attention","title":"Active Visual Exploration Based on Attention-Map Entropy","date":"2023-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apardyl/AME","path":"architectures/selectors.py","file_url":"https://github.com/apardyl/AME/blob/HEAD/architectures/selectors.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"dfb4c043722a654f","mcp_get_code":{"code_sha256":"dfb4c043722a654f"}},{"arxiv_id":"2303.05675","paper":"/paper/humanbench-towards-general-human-centric","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","date":"2023-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenGVLab/HumanBench","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d2b8be1e94eca236","mcp_get_code":{"code_sha256":"d2b8be1e94eca236"}},{"arxiv_id":"2303.04249","paper":"/paper/where-we-are-and-what-we-re-looking-at-query","title":"Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenes","date":"2023-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AHKerrigan/GeoGuessNet","path":"networks.py","file_url":"https://github.com/AHKerrigan/GeoGuessNet/blob/HEAD/networks.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fcce1bfcb9c57d74","mcp_get_code":{"code_sha256":"fcce1bfcb9c57d74"}},{"arxiv_id":"2302.13971","paper":"/paper/llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"akanyaani/miniLLAMA","path":"model.py","file_url":"https://github.com/akanyaani/miniLLAMA/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"00a9dc7ef03e2fcc","mcp_get_code":{"code_sha256":"00a9dc7ef03e2fcc"}},{"arxiv_id":"2302.11002","paper":"/paper/learning-physical-models-that-can-respect","title":"Learning Physical Models that Can Respect Conservation Laws","date":"2023-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/probconserv","path":"deep_pdes/attentive_neural_process/probconserv.py","file_url":"https://github.com/amazon-science/probconserv/blob/HEAD/deep_pdes/attentive_neural_process/probconserv.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bf3079228b4b66f8","mcp_get_code":{"code_sha256":"bf3079228b4b66f8"}},{"arxiv_id":"2302.05160","paper":"/paper/dual-memory-units-with-uncertainty-regulation","title":"Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection","date":"2023-02-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"henrryzh1/UR-DMU","path":"model.py","file_url":"https://github.com/henrryzh1/UR-DMU/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa81f706d91cb317","mcp_get_code":{"code_sha256":"aa81f706d91cb317"}},{"arxiv_id":"2302.01825","paper":"/paper/hdformer-high-order-directed-transformer-for","title":"HDFormer: High-order Directed Transformer for 3D Human Pose Estimation","date":"2023-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hyer/HDFormer","path":"models/hd_former.py","file_url":"https://github.com/hyer/HDFormer/blob/HEAD/models/hd_former.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d252bbacc051912d","mcp_get_code":{"code_sha256":"d252bbacc051912d"}},{"arxiv_id":"2301.10222","paper":"/paper/rangevit-towards-vision-transformers-for-3d","title":"RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving","date":"2023-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"valeoai/rangevit","path":"models/rangevit.py","file_url":"https://github.com/valeoai/rangevit/blob/HEAD/models/rangevit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cec164e8a2ce78c9","mcp_get_code":{"code_sha256":"cec164e8a2ce78c9"}},{"arxiv_id":"2301.08249","paper":"/paper/causal-conditional-hidden-markov-model-for","title":"Causal conditional hidden Markov model for multimodal traffic prediction","date":"2023-01-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EternityZY/CCHMM","path":"models/CausalHMM.py","file_url":"https://github.com/EternityZY/CCHMM/blob/HEAD/models/CausalHMM.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"597fc4a17fd92e8b","mcp_get_code":{"code_sha256":"597fc4a17fd92e8b"}},{"arxiv_id":"2301.08243","paper":"/paper/self-supervised-learning-from-images-with-a","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","date":"2023-01-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"waterdisappear/sar-jepa","path":"Pretraining/models_lomar.py","file_url":"https://github.com/waterdisappear/sar-jepa/blob/HEAD/Pretraining/models_lomar.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"d5d4d27df91c3a11","mcp_get_code":{"code_sha256":"d5d4d27df91c3a11"}},{"arxiv_id":"2301.04944","paper":"/paper/vits-for-sits-vision-transformers-for","title":"ViTs for SITS: Vision Transformers for Satellite Image Time Series","date":"2023-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"michaeltrs/DeepSatModels","path":"models/TSViT/TSViTcls.py","file_url":"https://github.com/michaeltrs/DeepSatModels/blob/HEAD/models/TSViT/TSViTcls.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7ff8cc1149fcdb55","mcp_get_code":{"code_sha256":"7ff8cc1149fcdb55"}},{"arxiv_id":"2301.01296","paper":"/paper/tinymim-an-empirical-study-of-distilling-mim","title":"TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models","date":"2023-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oliverrensu/d-igpt","path":"DiGPT_torch/models_digpt.py","file_url":"https://github.com/oliverrensu/d-igpt/blob/HEAD/DiGPT_torch/models_digpt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6fb43d8ac6c1d00c","mcp_get_code":{"code_sha256":"6fb43d8ac6c1d00c"}},{"arxiv_id":"2301.01296","paper":"/paper/tinymim-an-empirical-study-of-distilling-mim","title":"TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models","date":"2023-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OliverRensu/TinyMIM","path":"models_tinymim.py","file_url":"https://github.com/OliverRensu/TinyMIM/blob/HEAD/models_tinymim.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e861849da1498470","mcp_get_code":{"code_sha256":"e861849da1498470"}},{"arxiv_id":"2212.11972","paper":"/paper/scalable-adaptive-computation-for-iterative","title":"Scalable Adaptive Computation for Iterative Generation","date":"2022-12-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/recurrent-interface-network-pytorch","path":"rin_pytorch/rin_pytorch.py","file_url":"https://github.com/lucidrains/recurrent-interface-network-pytorch/blob/HEAD/rin_pytorch/rin_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"305ed1d536ee99b2","mcp_get_code":{"code_sha256":"305ed1d536ee99b2"}},{"arxiv_id":"2212.03465","paper":"/paper/mediar-harmony-of-data-centric-and-model","title":"MEDIAR: Harmony of Data-Centric and Model-Centric for Multi-Modality Microscopy","date":"2022-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joonkeekim/mediar-napari","path":"segmentation_models_pytorch/encoders/mix_transformer.py","file_url":"https://github.com/joonkeekim/mediar-napari/blob/HEAD/segmentation_models_pytorch/encoders/mix_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"9730b11fb54530b9","mcp_get_code":{"code_sha256":"9730b11fb54530b9"}},{"arxiv_id":"2212.02952","paper":"/paper/simple-baseline-for-weather-forecasting-using","title":"Simple Baseline for Weather Forecasting Using Spatiotemporal Context Aggregation Network","date":"2022-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seominseok0429/w4c22-simple-baseline-for-weather-forecasting-using-spatiotemporal-context-aggregation-network","path":"models/SIANet.py","file_url":"https://github.com/seominseok0429/w4c22-simple-baseline-for-weather-forecasting-using-spatiotemporal-context-aggregation-network/blob/HEAD/models/SIANet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"7156c7d4ad4752be","mcp_get_code":{"code_sha256":"7156c7d4ad4752be"}},{"arxiv_id":"2211.05187","paper":"/paper/training-a-vision-transformer-from-scratch-in","title":"Training a Vision Transformer from scratch in less than 24 hours with 1 GPU","date":"2022-11-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BorealisAI/efficient-vit-training","path":"models_vit/localvit.py","file_url":"https://github.com/BorealisAI/efficient-vit-training/blob/HEAD/models_vit/localvit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"914feb6bd11b62e4","mcp_get_code":{"code_sha256":"914feb6bd11b62e4"}},{"arxiv_id":"2210.11170","paper":"/paper/coordinates-are-not-lonely-codebook-prior","title":"Coordinates Are NOT Lonely -- Codebook Prior Helps Implicit Neural 3D Representations","date":"2022-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fukunyin/coco-nerf","path":"code/model/coco.py","file_url":"https://github.com/fukunyin/coco-nerf/blob/HEAD/code/model/coco.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dd67080fe3389024","mcp_get_code":{"code_sha256":"dd67080fe3389024"}},{"arxiv_id":"2210.11016","paper":"/paper/towards-sustainable-self-supervised-learning","title":"Towards Sustainable Self-supervised Learning","date":"2022-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/tec","path":"models/models_tec_vit.py","file_url":"https://github.com/sail-sg/tec/blob/HEAD/models/models_tec_vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bde9fdb88d04b910","mcp_get_code":{"code_sha256":"bde9fdb88d04b910"}},{"arxiv_id":"2210.10716","paper":"/paper/croco-self-supervised-pre-training-for-3d","title":"CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion","date":"2022-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver/croco","path":"models/croco.py","file_url":"https://github.com/naver/croco/blob/HEAD/models/croco.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e43d66926c52d73f","mcp_get_code":{"code_sha256":"e43d66926c52d73f"}},{"arxiv_id":"2210.10105","paper":"/paper/elastic-numerical-reasoning-with-adaptive","title":"ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler","date":"2022-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neurasearch/neurips-2022-submission-3358","path":"models/hierarchical_decoder.py","file_url":"https://github.com/neurasearch/neurips-2022-submission-3358/blob/HEAD/models/hierarchical_decoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2b0c4c189a5e9317","mcp_get_code":{"code_sha256":"2b0c4c189a5e9317"}},{"arxiv_id":"2210.08353","paper":"/paper/mgnni-multiscale-graph-neural-networks-with","title":"MGNNI: Multiscale Graph Neural Networks with Implicit Layers","date":"2022-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liu-jc/mgnni","path":"nodeclassification/models_heterophilic.py","file_url":"https://github.com/liu-jc/mgnni/blob/HEAD/nodeclassification/models_heterophilic.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"65d8053fa4d2df0a","mcp_get_code":{"code_sha256":"65d8053fa4d2df0a"}},{"arxiv_id":"2210.08189","paper":"/paper/parameter-free-dynamic-graph-embedding-for","title":"Parameter-free Dynamic Graph Embedding for Link Prediction","date":"2022-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fudancisl/freegem","path":"next-interaction-prediction/process.py","file_url":"https://github.com/fudancisl/freegem/blob/HEAD/next-interaction-prediction/process.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3c9763a6b2b73048","mcp_get_code":{"code_sha256":"3c9763a6b2b73048"}},{"arxiv_id":"2210.03952","paper":"/paper/detaching-and-boosting-dual-engine-for-scale","title":"Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth Estimation","date":"2022-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"attackonmuggle/dab_net0","path":"Pytorch/mono/model/mono_hrnet/depth_decoder.py","file_url":"https://github.com/attackonmuggle/dab_net0/blob/HEAD/Pytorch/mono/model/mono_hrnet/depth_decoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6e605fe157361125","mcp_get_code":{"code_sha256":"6e605fe157361125"}},{"arxiv_id":"2210.01427","paper":"/paper/accurate-image-restoration-with-attention","title":"Accurate Image Restoration with Attention Retractable Transformer","date":"2022-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gladzhang/art","path":"basicsr/archs/art_arch.py","file_url":"https://github.com/gladzhang/art/blob/HEAD/basicsr/archs/art_arch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fe1598fcd19fedfc","mcp_get_code":{"code_sha256":"fe1598fcd19fedfc"}},{"arxiv_id":"2209.14156","paper":"/paper/tvlt-textless-vision-language-transformer","title":"TVLT: Textless Vision-Language Transformer","date":"2022-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zinengtang/tvlt","path":"model/modules/tvlt.py","file_url":"https://github.com/zinengtang/tvlt/blob/HEAD/model/modules/tvlt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f34c6d56e7d5f8fa","mcp_get_code":{"code_sha256":"f34c6d56e7d5f8fa"}},{"arxiv_id":"2209.08956","paper":"/paper/panoramic-vision-transformer-for-saliency","title":"Panoramic Vision Transformer for Saliency Detection in 360° Videos","date":"2022-09-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hs-yn/paver","path":"code/model/decoder.py","file_url":"https://github.com/hs-yn/paver/blob/HEAD/code/model/decoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cc958048d557e1e9","mcp_get_code":{"code_sha256":"cc958048d557e1e9"}},{"arxiv_id":"2209.07947","paper":"/paper/omni-dimensional-dynamic-convolution-1","title":"Omni-Dimensional Dynamic Convolution","date":"2022-09-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"osvai/odconv","path":"modules/odconv.py","file_url":"https://github.com/osvai/odconv/blob/HEAD/modules/odconv.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"aa2a4891ff29d62f","mcp_get_code":{"code_sha256":"aa2a4891ff29d62f"}},{"arxiv_id":"2209.05588","paper":"/paper/centerformer-center-based-transformer-for-3d","title":"CenterFormer: Center-based Transformer for 3D Object Detection","date":"2022-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TuSimple/centerformer","path":"det3d/models/utils/transformer.py","file_url":"https://github.com/TuSimple/centerformer/blob/HEAD/det3d/models/utils/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f275792db636f6c2","mcp_get_code":{"code_sha256":"f275792db636f6c2"}},{"arxiv_id":"2209.04439","paper":"/paper/improved-masked-image-generation-with-token","title":"Improved Masked Image Generation with Token-Critic","date":"2022-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/phenaki-pytorch","path":"phenaki_pytorch/phenaki_pytorch.py","file_url":"https://github.com/lucidrains/phenaki-pytorch/blob/HEAD/phenaki_pytorch/phenaki_pytorch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"20759ff768a1ec91","mcp_get_code":{"code_sha256":"20759ff768a1ec91"}},{"arxiv_id":"2208.11844","paper":"/paper/unbiased-multi-modality-guidance-for-image","title":"Unbiased Multi-Modality Guidance for Image Inpainting","date":"2022-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yeates/MMT","path":"modules/MMT.py","file_url":"https://github.com/yeates/MMT/blob/HEAD/modules/MMT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2886ab71fc45d94b","mcp_get_code":{"code_sha256":"2886ab71fc45d94b"}},{"arxiv_id":"2208.03550","paper":"/paper/frozen-clip-models-are-efficient-video","title":"Frozen CLIP Models are Efficient Video Learners","date":"2022-08-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenGVLab/efficient-video-recognition","path":"model.py","file_url":"https://github.com/OpenGVLab/efficient-video-recognition/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"68359211beb5845f","mcp_get_code":{"code_sha256":"68359211beb5845f"}},{"arxiv_id":"2207.13298","paper":"/paper/is-attention-all-nerf-needs","title":"Is Attention All That NeRF Needs?","date":"2022-07-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vita-group/gnt","path":"gnt/transformer_network.py","file_url":"https://github.com/vita-group/gnt/blob/HEAD/gnt/transformer_network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0c8d8666ea836326","mcp_get_code":{"code_sha256":"0c8d8666ea836326"}},{"arxiv_id":"2207.10666","paper":"/paper/tinyvit-fast-pretraining-distillation-for","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","date":"2022-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/cream","path":"TinyViT/models/tiny_vit.py","file_url":"https://github.com/microsoft/cream/blob/HEAD/TinyViT/models/tiny_vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3f95a13fec53515d","mcp_get_code":{"code_sha256":"3f95a13fec53515d"}},{"arxiv_id":"2207.10447","paper":"/paper/weakly-supervised-object-localization-via","title":"Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration","date":"2022-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"164140757/SCM","path":"lib/models/deit.py","file_url":"https://github.com/164140757/SCM/blob/HEAD/lib/models/deit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ce23b9a90f7e4277","mcp_get_code":{"code_sha256":"ce23b9a90f7e4277"}},{"arxiv_id":"2207.09685","paper":"/paper/bigcolor-colorization-using-a-generative","title":"BigColor: Colorization using a Generative Color Prior for Natural Images","date":"2022-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KIMGEONUNG/BigColor","path":"models/encoders.py","file_url":"https://github.com/KIMGEONUNG/BigColor/blob/HEAD/models/encoders.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6160652bb10a2038","mcp_get_code":{"code_sha256":"6160652bb10a2038"}},{"arxiv_id":"2207.08132","paper":"/paper/e-nerv-expedite-neural-video-representation","title":"E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context","date":"2022-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kyleleey/E-NeRV","path":"model/E_NeRV.py","file_url":"https://github.com/kyleleey/E-NeRV/blob/HEAD/model/E_NeRV.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2f960dd455ebf156","mcp_get_code":{"code_sha256":"2f960dd455ebf156"}},{"arxiv_id":"2207.07116","paper":"/paper/bootstrapped-masked-autoencoders-for-vision","title":"Bootstrapped Masked Autoencoders for Vision BERT Pretraining","date":"2022-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LightDXY/BootMAE","path":"models/modeling_pretrain_bootmae.py","file_url":"https://github.com/LightDXY/BootMAE/blob/HEAD/models/modeling_pretrain_bootmae.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dc9091be97d3adb7","mcp_get_code":{"code_sha256":"dc9091be97d3adb7"}},{"arxiv_id":"2207.06405","paper":"/paper/masked-autoencoders-that-listen","title":"Masked Autoencoders that Listen","date":"2022-07-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rishikksh20/AudioMAE-pytorch","path":"audio_mae.py","file_url":"https://github.com/rishikksh20/AudioMAE-pytorch/blob/HEAD/audio_mae.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bd6d4930cb3f2f8","mcp_get_code":{"code_sha256":"3bd6d4930cb3f2f8"}},{"arxiv_id":"2207.06101","paper":"/paper/global-local-motion-transformer-for","title":"Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning","date":"2022-07-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Boeun-Kim/GL-Transformer","path":"model/transformer.py","file_url":"https://github.com/Boeun-Kim/GL-Transformer/blob/HEAD/model/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c16c5275e7180f5e","mcp_get_code":{"code_sha256":"c16c5275e7180f5e"}},{"arxiv_id":"2206.09104","paper":"/paper/score-guided-intermediate-layer-optimization","title":"Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems","date":"2022-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"giannisdaras/ilo","path":"ilo_biggan.py","file_url":"https://github.com/giannisdaras/ilo/blob/HEAD/ilo_biggan.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0eda3d4423cde1b8","mcp_get_code":{"code_sha256":"0eda3d4423cde1b8"}},{"arxiv_id":"2205.05277","paper":"/paper/aggpose-deep-aggregation-vision-transformer","title":"AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimation","date":"2022-05-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SZAR-LAB/AggPose","path":"lib/models/pose_aggpose.py","file_url":"https://github.com/SZAR-LAB/AggPose/blob/HEAD/lib/models/pose_aggpose.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"58193b289e41db55","mcp_get_code":{"code_sha256":"58193b289e41db55"}},{"arxiv_id":"2205.03806","paper":"/paper/transformer-tracking-with-cyclic-shifting","title":"Transformer Tracking with Cyclic Shifting Window Attention","date":"2022-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SkyeSong38/CSWinTT","path":"lib/models/cswintt/transformer_cs.py","file_url":"https://github.com/SkyeSong38/CSWinTT/blob/HEAD/lib/models/cswintt/transformer_cs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59d31f3151914df3","mcp_get_code":{"code_sha256":"59d31f3151914df3"}},{"arxiv_id":"2204.12484","paper":"/paper/vitpose-simple-vision-transformer-baselines","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","date":"2022-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gpastal24/ViTPose-Pytorch","path":"src/vitpose_infer/builder/backbones/vit.py","file_url":"https://github.com/gpastal24/ViTPose-Pytorch/blob/HEAD/src/vitpose_infer/builder/backbones/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"a17528cd8209371a","mcp_get_code":{"code_sha256":"a17528cd8209371a"}},{"arxiv_id":"2204.09975","paper":"/paper/eliminating-backdoor-triggers-for-deep-neural","title":"Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation","date":"2022-04-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BililiCode/ARGD","path":"riman_distance.py","file_url":"https://github.com/BililiCode/ARGD/blob/HEAD/riman_distance.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d6ce78123dac409c","mcp_get_code":{"code_sha256":"d6ce78123dac409c"}},{"arxiv_id":"2204.09331","paper":"/paper/nformer-robust-person-re-identification-with","title":"NFormer: Robust Person Re-identification with Neighbor Transformer","date":"2022-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haochenheheda/nformer","path":"modeling/nformer.py","file_url":"https://github.com/haochenheheda/nformer/blob/HEAD/modeling/nformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"23ee5863ec3c9b2d","mcp_get_code":{"code_sha256":"23ee5863ec3c9b2d"}},{"arxiv_id":"2204.07683","paper":"/paper/safe-self-refinement-for-transformer-based","title":"Safe Self-Refinement for Transformer-based Domain Adaptation","date":"2022-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tsun/SSRT","path":"model/SSRT.py","file_url":"https://github.com/tsun/SSRT/blob/HEAD/model/SSRT.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bbf9328517c62d43","mcp_get_code":{"code_sha256":"bbf9328517c62d43"}},{"arxiv_id":"2204.04627","paper":"/paper/stripformer-strip-transformer-for-fast-image","title":"Stripformer: Strip Transformer for Fast Image Deblurring","date":"2022-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pp00704831/Stripformer","path":"models/Stripformer.py","file_url":"https://github.com/pp00704831/Stripformer/blob/HEAD/models/Stripformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"86ce74bd6f20dd97","mcp_get_code":{"code_sha256":"86ce74bd6f20dd97"}},{"arxiv_id":"2204.01955","paper":"/paper/autoregressive-3d-shape-generation-via","title":"Autoregressive 3D Shape Generation via Canonical Mapping","date":"2022-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AnjieCheng/CanonicalVAE","path":"src/canonicalvq/models/decoder.py","file_url":"https://github.com/AnjieCheng/CanonicalVAE/blob/HEAD/src/canonicalvq/models/decoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5912657dc7302073","mcp_get_code":{"code_sha256":"5912657dc7302073"}},{"arxiv_id":"2204.01697","paper":"/paper/maxvit-multi-axis-vision-transformer","title":"MaxViT: Multi-Axis Vision Transformer","date":"2022-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/maxvit","path":"maxvit/models/maxvit.py","file_url":"https://github.com/google-research/maxvit/blob/HEAD/maxvit/models/maxvit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2bc733f08e821139","mcp_get_code":{"code_sha256":"2bc733f08e821139"}},{"arxiv_id":"2204.01697","paper":"/paper/maxvit-multi-axis-vision-transformer","title":"MaxViT: Multi-Axis Vision Transformer","date":"2022-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/vit-pytorch","path":"vit_pytorch/max_vit.py","file_url":"https://github.com/lucidrains/vit-pytorch/blob/HEAD/vit_pytorch/max_vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0ff4fe4361d49089","mcp_get_code":{"code_sha256":"0ff4fe4361d49089"}},{"arxiv_id":"2204.00993","paper":"/paper/improving-vision-transformers-by-revisiting","title":"Improving Vision Transformers by Revisiting High-frequency Components","date":"2022-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiawangbai/HAT","path":"models/volo.py","file_url":"https://github.com/jiawangbai/HAT/blob/HEAD/models/volo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"758bd44a54df5709","mcp_get_code":{"code_sha256":"758bd44a54df5709"}},{"arxiv_id":"2203.15556","paper":"/paper/training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"karpathy/llama2.c","path":"model.py","file_url":"https://github.com/karpathy/llama2.c/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c20a31b2d7615a4b","mcp_get_code":{"code_sha256":"c20a31b2d7615a4b"}},{"arxiv_id":"2203.15371","paper":"/paper/mc-beit-multi-choice-discretization-for-image","title":"mc-BEiT: Multi-choice Discretization for Image BERT Pre-training","date":"2022-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lixiaotong97/mc-BEiT","path":"modeling_pretrain.py","file_url":"https://github.com/lixiaotong97/mc-BEiT/blob/HEAD/modeling_pretrain.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2cddf6be601c390b","mcp_get_code":{"code_sha256":"2cddf6be601c390b"}},{"arxiv_id":"2203.15216","paper":"/paper/affine-medical-image-registration-with-coarse","title":"Affine Medical Image Registration with Coarse-to-Fine Vision Transformer","date":"2022-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cwmok/C2FViT","path":"Code/C2FViT_model.py","file_url":"https://github.com/cwmok/C2FViT/blob/HEAD/Code/C2FViT_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bf29ef6ce3743333","mcp_get_code":{"code_sha256":"bf29ef6ce3743333"}},{"arxiv_id":"2203.12119","paper":"/paper/visual-prompt-tuning","title":"Visual Prompt Tuning","date":"2022-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wgcban/apt","path":"modeling_VPT.py","file_url":"https://github.com/wgcban/apt/blob/HEAD/modeling_VPT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"bc0e89d4bae92c5f","mcp_get_code":{"code_sha256":"bc0e89d4bae92c5f"}},{"arxiv_id":"2203.08913","paper":"/paper/memorizing-transformers-1","title":"Memorizing Transformers","date":"2022-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/memorizing-transformers-pytorch","path":"memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","file_url":"https://github.com/lucidrains/memorizing-transformers-pytorch/blob/HEAD/memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4673cf1999dcca6b","mcp_get_code":{"code_sha256":"4673cf1999dcca6b"}},{"arxiv_id":"2203.08243","paper":"/paper/unified-visual-transformer-compression-1","title":"Unified Visual Transformer Compression","date":"2022-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/UVC","path":"UVC/models/modeling.py","file_url":"https://github.com/VITA-Group/UVC/blob/HEAD/UVC/models/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bfc8fe0ddf96d4c7","mcp_get_code":{"code_sha256":"bfc8fe0ddf96d4c7"}},{"arxiv_id":"2203.07852","paper":"/paper/block-recurrent-transformers","title":"Block-Recurrent Transformers","date":"2022-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/block-recurrent-transformer-pytorch","path":"block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py","file_url":"https://github.com/lucidrains/block-recurrent-transformer-pytorch/blob/HEAD/block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"20f6b4952e3785e4","mcp_get_code":{"code_sha256":"20f6b4952e3785e4"}},{"arxiv_id":"2203.03598","paper":"/paper/audio-visual-generalised-zero-shot-learning","title":"Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language","date":"2022-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ExplainableML/AVCA-GZSL","path":"src/model_improvements.py","file_url":"https://github.com/ExplainableML/AVCA-GZSL/blob/HEAD/src/model_improvements.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"de7ce81032c8b359","mcp_get_code":{"code_sha256":"de7ce81032c8b359"}},{"arxiv_id":"2203.02891","paper":"/paper/multi-class-token-transformer-for-weakly","title":"Multi-class Token Transformer for Weakly Supervised Semantic Segmentation","date":"2022-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xulianuwa/mctformer","path":"models.py","file_url":"https://github.com/xulianuwa/mctformer/blob/HEAD/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d910749427fb67f1","mcp_get_code":{"code_sha256":"d910749427fb67f1"}},{"arxiv_id":"2203.01601","paper":"/paper/syntax-aware-network-for-handwritten","title":"Syntax-Aware Network for Handwritten Mathematical Expression Recognition","date":"2022-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tal-tech/san","path":"models/Hierarchical_attention/decoder.py","file_url":"https://github.com/tal-tech/san/blob/HEAD/models/Hierarchical_attention/decoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"204a7c15bb553044","mcp_get_code":{"code_sha256":"204a7c15bb553044"}},{"arxiv_id":"2203.00859","paper":"/paper/mixste-seq2seq-mixed-spatio-temporal-encoder","title":"MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video","date":"2022-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JinluZhang1126/MixSTE","path":"common/model_cross.py","file_url":"https://github.com/JinluZhang1126/MixSTE/blob/HEAD/common/model_cross.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a54bb4e29b966532","mcp_get_code":{"code_sha256":"a54bb4e29b966532"}},{"arxiv_id":"2202.10108","paper":"/paper/vitaev2-vision-transformer-advanced-by","title":"ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond","date":"2022-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yangyucheng000/papercode-2","path":"STViT-Mindspore-main/models/stvit.py","file_url":"https://github.com/yangyucheng000/papercode-2/blob/HEAD/STViT-Mindspore-main/models/stvit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3fefa875010c6edf","mcp_get_code":{"code_sha256":"3fefa875010c6edf"}},{"arxiv_id":"2202.05492","paper":"/paper/entroformer-a-transformer-based-entropy-model-1","title":"Entroformer: A Transformer-based Entropy Model for Learned Image Compression","date":"2022-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mx54039q/entroformer","path":"module/entroformer.py","file_url":"https://github.com/mx54039q/entroformer/blob/HEAD/module/entroformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b56b436f1b6c3bda","mcp_get_code":{"code_sha256":"b56b436f1b6c3bda"}},{"arxiv_id":"2202.04200","paper":"/paper/maskgit-masked-generative-image-transformer","title":"MaskGIT: Masked Generative Image Transformer","date":"2022-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"valeoai/maskgit-pytorch","path":"Network/transformer.py","file_url":"https://github.com/valeoai/maskgit-pytorch/blob/HEAD/Network/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7fd4e0ce7bd6b27f","mcp_get_code":{"code_sha256":"7fd4e0ce7bd6b27f"}},{"arxiv_id":"2202.04200","paper":"/paper/maskgit-masked-generative-image-transformer","title":"MaskGIT: Masked Generative Image Transformer","date":"2022-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LAION-AI/phenaki","path":"maskgit.py","file_url":"https://github.com/LAION-AI/phenaki/blob/HEAD/maskgit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7e79dc89343596b8","mcp_get_code":{"code_sha256":"7e79dc89343596b8"}},{"arxiv_id":"2202.02514","paper":"/paper/score-based-generative-modeling-of-graphs-via","title":"Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations","date":"2022-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AdrienC21/CCSD","path":"ccsd/src/models/ScoreNetwork_A.py","file_url":"https://github.com/AdrienC21/CCSD/blob/HEAD/ccsd/src/models/ScoreNetwork_A.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7b774bdd34c82a39","mcp_get_code":{"code_sha256":"7b774bdd34c82a39"}},{"arxiv_id":"2202.02514","paper":"/paper/score-based-generative-modeling-of-graphs-via","title":"Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations","date":"2022-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"harryjo97/gdss","path":"models/ScoreNetwork_A.py","file_url":"https://github.com/harryjo97/gdss/blob/HEAD/models/ScoreNetwork_A.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"33bc3c99206d9a3e","mcp_get_code":{"code_sha256":"33bc3c99206d9a3e"}},{"arxiv_id":"2201.00814","paper":"/paper/vision-transformer-slimming-multi-dimension","title":"Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space","date":"2022-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arnav0400/vit-slim","path":"ViT-Slim/models/layers.py","file_url":"https://github.com/arnav0400/vit-slim/blob/HEAD/ViT-Slim/models/layers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b5047c4b9740519e","mcp_get_code":{"code_sha256":"b5047c4b9740519e"}},{"arxiv_id":"2112.04426","paper":"/paper/improving-language-models-by-retrieving-from","title":"Improving language models by retrieving from trillions of tokens","date":"2021-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/RETRO-pytorch","path":"retro_pytorch/retro_pytorch.py","file_url":"https://github.com/lucidrains/RETRO-pytorch/blob/HEAD/retro_pytorch/retro_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"03b81e2f9a4d2d4c","mcp_get_code":{"code_sha256":"03b81e2f9a4d2d4c"}},{"arxiv_id":"2111.06377","paper":"/paper/masked-autoencoders-are-scalable-vision","title":"Masked Autoencoders Are Scalable Vision Learners","date":"2021-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DarshanDeshpande/jax-models","path":"jax_models/models/masked_autoencoder.py","file_url":"https://github.com/DarshanDeshpande/jax-models/blob/HEAD/jax_models/models/masked_autoencoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2caebdfa70d265d1","mcp_get_code":{"code_sha256":"2caebdfa70d265d1"}},{"arxiv_id":"2111.06377","paper":"/paper/masked-autoencoders-are-scalable-vision","title":"Masked Autoencoders Are Scalable Vision Learners","date":"2021-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hkbu-vscomputing/2022_mm_dmae-mocap","path":"model/dmae.py","file_url":"https://github.com/hkbu-vscomputing/2022_mm_dmae-mocap/blob/HEAD/model/dmae.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"331e0a44942a0951","mcp_get_code":{"code_sha256":"331e0a44942a0951"}},{"arxiv_id":"2111.06377","paper":"/paper/masked-autoencoders-are-scalable-vision","title":"Masked Autoencoders Are Scalable Vision Learners","date":"2021-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liujiyuan13/MAE-code","path":"model.py","file_url":"https://github.com/liujiyuan13/MAE-code/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"5671450eaed4b12b","mcp_get_code":{"code_sha256":"5671450eaed4b12b"}},{"arxiv_id":"2111.06377","paper":"/paper/masked-autoencoders-are-scalable-vision","title":"Masked Autoencoders Are Scalable Vision Learners","date":"2021-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangsr126/mae-lite","path":"projects/mae_lite/models_mae.py","file_url":"https://github.com/wangsr126/mae-lite/blob/HEAD/projects/mae_lite/models_mae.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"52e133864e98cbdc","mcp_get_code":{"code_sha256":"52e133864e98cbdc"}},{"arxiv_id":"2111.06377","paper":"/paper/masked-autoencoders-are-scalable-vision","title":"Masked Autoencoders Are Scalable Vision Learners","date":"2021-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guilk/vlc","path":"vlc/modules/mae_transformer.py","file_url":"https://github.com/guilk/vlc/blob/HEAD/vlc/modules/mae_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b1605707f77d1785","mcp_get_code":{"code_sha256":"b1605707f77d1785"}},{"arxiv_id":"2111.06377","paper":"/paper/masked-autoencoders-are-scalable-vision","title":"Masked Autoencoders Are Scalable Vision Learners","date":"2021-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yangsun22/tc-moa","path":"model/ViT_MAE.py","file_url":"https://github.com/yangsun22/tc-moa/blob/HEAD/model/ViT_MAE.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ab6e3fb020aef3ab","mcp_get_code":{"code_sha256":"ab6e3fb020aef3ab"}},{"arxiv_id":"2111.02521","paper":"/paper/sequence-to-sequence-modeling-for-action-1","title":"Sequence-to-Sequence Modeling for Action Identification at High Temporal Resolution","date":"2021-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aakashrkaku/seq2seq_hrar","path":"imu_data/las_model.py","file_url":"https://github.com/aakashrkaku/seq2seq_hrar/blob/HEAD/imu_data/las_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"32349d8900b86ecd","mcp_get_code":{"code_sha256":"32349d8900b86ecd"}},{"arxiv_id":"2110.13430","paper":"/paper/contextual-similarity-aggregation-with-self","title":"Contextual Similarity Aggregation with Self-attention for Visual Re-ranking","date":"2021-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mcc-wh/csa","path":"network/RerankTransformer.py","file_url":"https://github.com/mcc-wh/csa/blob/HEAD/network/RerankTransformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6edc8b341a07610c","mcp_get_code":{"code_sha256":"6edc8b341a07610c"}},{"arxiv_id":"2110.02178","paper":"/paper/mobilevit-light-weight-general-purpose-and","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","date":"2021-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jaiwei98/mobile-vit-pytorch","path":"mobile_vit/mobilevit.py","file_url":"https://github.com/jaiwei98/mobile-vit-pytorch/blob/HEAD/mobile_vit/mobilevit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7dce48772b2e159a","mcp_get_code":{"code_sha256":"7dce48772b2e159a"}},{"arxiv_id":"2110.02178","paper":"/paper/mobilevit-light-weight-general-purpose-and","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","date":"2021-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"murufeng/awesome_lightweight_networks","path":"light_cnns/Transformer/mobile_vit.py","file_url":"https://github.com/murufeng/awesome_lightweight_networks/blob/HEAD/light_cnns/Transformer/mobile_vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"43531c7c47f675ef","mcp_get_code":{"code_sha256":"43531c7c47f675ef"}},{"arxiv_id":"2110.02178","paper":"/paper/mobilevit-light-weight-general-purpose-and","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","date":"2021-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xmu-xiaoma666/External-Attention-pytorch","path":"model/backbone/MobileViT.py","file_url":"https://github.com/xmu-xiaoma666/External-Attention-pytorch/blob/HEAD/model/backbone/MobileViT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d55210e5cfb23cea","mcp_get_code":{"code_sha256":"d55210e5cfb23cea"}},{"arxiv_id":"2110.02178","paper":"/paper/mobilevit-light-weight-general-purpose-and","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","date":"2021-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kornia/kornia","path":"kornia/models/vit_mobile.py","file_url":"https://github.com/kornia/kornia/blob/HEAD/kornia/models/vit_mobile.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2230f658d6c25822","mcp_get_code":{"code_sha256":"2230f658d6c25822"}},{"arxiv_id":"2109.07812","paper":"/paper/transductive-learning-for-unsupervised-text","title":"Transductive Learning for Unsupervised Text Style Transfer","date":"2021-09-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaofei05/tsst","path":"model/TSST.py","file_url":"https://github.com/xiaofei05/tsst/blob/HEAD/model/TSST.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d66300e7c5ca2267","mcp_get_code":{"code_sha256":"d66300e7c5ca2267"}},{"arxiv_id":"2109.04096","paper":"/paper/a-three-stage-learning-framework-for-low","title":"A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation","date":"2021-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neukg/KAT-TSLF","path":"kat/modeling.py","file_url":"https://github.com/neukg/KAT-TSLF/blob/HEAD/kat/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"076a62f8319088ad","mcp_get_code":{"code_sha256":"076a62f8319088ad"}},{"arxiv_id":"2109.02974","paper":"/paper/fuseformer-fusing-fine-grained-information-in","title":"FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting","date":"2021-09-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruiliu-ai/FuseFormer","path":"model/fuseformer.py","file_url":"https://github.com/ruiliu-ai/FuseFormer/blob/HEAD/model/fuseformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a702c7ce4cea9802","mcp_get_code":{"code_sha256":"a702c7ce4cea9802"}},{"arxiv_id":"2108.06693","paper":"/paper/exploring-temporal-coherence-for-more-general","title":"Exploring Temporal Coherence for More General Video Face Forgery Detection","date":"2021-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yinglinzheng/FTCN","path":"model/classifier/time_transformer.py","file_url":"https://github.com/yinglinzheng/FTCN/blob/HEAD/model/classifier/time_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1fa35a8f1e7d3dbe","mcp_get_code":{"code_sha256":"1fa35a8f1e7d3dbe"}},{"arxiv_id":"2107.14795","paper":"/paper/perceiver-io-a-general-architecture-for","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","date":"2021-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/perceiver-pytorch","path":"perceiver_pytorch/perceiver_io.py","file_url":"https://github.com/lucidrains/perceiver-pytorch/blob/HEAD/perceiver_pytorch/perceiver_io.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cc13268d4214ea66","mcp_get_code":{"code_sha256":"cc13268d4214ea66"}},{"arxiv_id":"2107.08918","paper":"/paper/self-promoted-prototype-refinement-for-few-1","title":"Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning","date":"2021-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhukaii/SPPR","path":"utils/model/my_model.py","file_url":"https://github.com/zhukaii/SPPR/blob/HEAD/utils/model/my_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7f4e4bf045a4c464","mcp_get_code":{"code_sha256":"7f4e4bf045a4c464"}},{"arxiv_id":"2107.05407","paper":"/paper/pondernet-learning-to-ponder","title":"PonderNet: Learning to Ponder","date":"2021-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/ponder-transformer","path":"ponder_transformer/ponder_transformer.py","file_url":"https://github.com/lucidrains/ponder-transformer/blob/HEAD/ponder_transformer/ponder_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2bca9856715b9238","mcp_get_code":{"code_sha256":"2bca9856715b9238"}},{"arxiv_id":"2107.04589","paper":"/paper/vitgan-training-gans-with-vision-transformers","title":"ViTGAN: Training GANs with Vision Transformers","date":"2021-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/parti-pytorch","path":"parti_pytorch/vit_vqgan.py","file_url":"https://github.com/lucidrains/parti-pytorch/blob/HEAD/parti_pytorch/vit_vqgan.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e2a8ba11e0a8cc86","mcp_get_code":{"code_sha256":"e2a8ba11e0a8cc86"}},{"arxiv_id":"2107.04589","paper":"/paper/vitgan-training-gans-with-vision-transformers","title":"ViTGAN: Training GANs with Vision Transformers","date":"2021-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wilile26811249/ViTGAN","path":"models.py","file_url":"https://github.com/wilile26811249/ViTGAN/blob/HEAD/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d4e0313631ba260f","mcp_get_code":{"code_sha256":"d4e0313631ba260f"}},{"arxiv_id":"2106.05304","paper":"/paper/revisiting-point-cloud-shape-classification","title":"Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline","date":"2021-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"axeber01/point-tnt","path":"model.py","file_url":"https://github.com/axeber01/point-tnt/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"15cfb9f4479acd04","mcp_get_code":{"code_sha256":"15cfb9f4479acd04"}},{"arxiv_id":"2106.04533","paper":"/paper/chasing-sparsity-in-vision-transformers-an","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","date":"2021-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/SViTE","path":"SViTE/dst_utils/core.py","file_url":"https://github.com/VITA-Group/SViTE/blob/HEAD/SViTE/dst_utils/core.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"07b68690a098d7e6","mcp_get_code":{"code_sha256":"07b68690a098d7e6"}},{"arxiv_id":"2106.02689","paper":"/paper/regionvit-regional-to-local-attention-for","title":"RegionViT: Regional-to-Local Attention for Vision Transformers","date":"2021-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"conceptofmind/Region-ViT-flax","path":"region_vit_flax.py","file_url":"https://github.com/conceptofmind/Region-ViT-flax/blob/HEAD/region_vit_flax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"43d3378c696e6de4","mcp_get_code":{"code_sha256":"43d3378c696e6de4"}},{"arxiv_id":"2106.02034","paper":"/paper/dynamicvit-efficient-vision-transformers-with","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","date":"2021-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raoyongming/DynamicViT","path":"models/dyvit.py","file_url":"https://github.com/raoyongming/DynamicViT/blob/HEAD/models/dyvit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"575ff52688baea94","mcp_get_code":{"code_sha256":"575ff52688baea94"}},{"arxiv_id":"2105.15203","paper":"/paper/segformer-simple-and-efficient-design-for","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","date":"2021-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IMvision12/SegFormer-tf","path":"models/segformer.py","file_url":"https://github.com/IMvision12/SegFormer-tf/blob/HEAD/models/segformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c26b3dcb83805d8b","mcp_get_code":{"code_sha256":"c26b3dcb83805d8b"}},{"arxiv_id":"2105.08050","paper":"/paper/pay-attention-to-mlps","title":"Pay Attention to MLPs","date":"2021-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/g-mlp-pytorch","path":"g_mlp_pytorch/g_mlp_pytorch.py","file_url":"https://github.com/lucidrains/g-mlp-pytorch/blob/HEAD/g_mlp_pytorch/g_mlp_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"444b2d5ae8422156","mcp_get_code":{"code_sha256":"444b2d5ae8422156"}},{"arxiv_id":"2105.08050","paper":"/paper/pay-attention-to-mlps","title":"Pay Attention to MLPs","date":"2021-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/g-mlp-gpt","path":"g_mlp_gpt/g_mlp_gpt.py","file_url":"https://github.com/lucidrains/g-mlp-gpt/blob/HEAD/g_mlp_gpt/g_mlp_gpt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"400cf93bc9a76062","mcp_get_code":{"code_sha256":"400cf93bc9a76062"}},{"arxiv_id":"2105.08050","paper":"/paper/pay-attention-to-mlps","title":"Pay Attention to MLPs","date":"2021-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/mlp-gpt-jax","path":"mlp_gpt_jax/mlp_gpt_jax.py","file_url":"https://github.com/lucidrains/mlp-gpt-jax/blob/HEAD/mlp_gpt_jax/mlp_gpt_jax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"01675e7e7c713147","mcp_get_code":{"code_sha256":"01675e7e7c713147"}},{"arxiv_id":"2105.07542","paper":"/paper/collaborative-graph-learning-with-auxiliary","title":"Collaborative Graph Learning with Auxiliary Text for Temporal Event Prediction in Healthcare","date":"2021-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LuChang-CS/CGL","path":"models/model.py","file_url":"https://github.com/LuChang-CS/CGL/blob/HEAD/models/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"926c550cbbfdfac9","mcp_get_code":{"code_sha256":"926c550cbbfdfac9"}},{"arxiv_id":"2105.03889","paper":"/paper/conformer-local-features-coupling-global","title":"Conformer: Local Features Coupling Global Representations for Visual Recognition","date":"2021-05-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vasgaowei/TS-CAM","path":"lib/models/conformer.py","file_url":"https://github.com/vasgaowei/TS-CAM/blob/HEAD/lib/models/conformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6dcea70dafba08f4","mcp_get_code":{"code_sha256":"6dcea70dafba08f4"}},{"arxiv_id":"2104.12099","paper":"/paper/visual-saliency-transformer","title":"Visual Saliency Transformer","date":"2021-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nnizhang/VST","path":"RGBD_VST/Models/Transformer.py","file_url":"https://github.com/nnizhang/VST/blob/HEAD/RGBD_VST/Models/Transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e518414e453d6bd4","mcp_get_code":{"code_sha256":"e518414e453d6bd4"}},{"arxiv_id":"2104.12099","paper":"/paper/visual-saliency-transformer","title":"Visual Saliency Transformer","date":"2021-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fhshen2022/prunerepaint","path":"RGB_VST/Models/t2t_vit.py","file_url":"https://github.com/fhshen2022/prunerepaint/blob/HEAD/RGB_VST/Models/t2t_vit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f6f001c7931d49f2","mcp_get_code":{"code_sha256":"f6f001c7931d49f2"}},{"arxiv_id":"2104.01136","paper":"/paper/levit-a-vision-transformer-in-convnet-s","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","date":"2021-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ahmedelmahy/myownvit","path":"vit_pytorch/levit.py","file_url":"https://github.com/ahmedelmahy/myownvit/blob/HEAD/vit_pytorch/levit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1e3d5a2962c6d68e","mcp_get_code":{"code_sha256":"1e3d5a2962c6d68e"}},{"arxiv_id":"2104.01136","paper":"/paper/levit-a-vision-transformer-in-convnet-s","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","date":"2021-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gatech-eic/vitcod","path":"Algorithm/levit/levit.py","file_url":"https://github.com/gatech-eic/vitcod/blob/HEAD/Algorithm/levit/levit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a70f356fb000eeaf","mcp_get_code":{"code_sha256":"a70f356fb000eeaf"}},{"arxiv_id":"2104.01136","paper":"/paper/levit-a-vision-transformer-in-convnet-s","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","date":"2021-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/LeViT","path":"levit.py","file_url":"https://github.com/facebookresearch/LeViT/blob/HEAD/levit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f75bc648af8ba051","mcp_get_code":{"code_sha256":"f75bc648af8ba051"}},{"arxiv_id":"2104.01136","paper":"/paper/levit-a-vision-transformer-in-convnet-s","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","date":"2021-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"conceptofmind/LeViT-flax","path":"levit.py","file_url":"https://github.com/conceptofmind/LeViT-flax/blob/HEAD/levit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9a030b11684381a9","mcp_get_code":{"code_sha256":"9a030b11684381a9"}},{"arxiv_id":"2104.00298","paper":"/paper/efficientnetv2-smaller-models-and-faster","title":"EfficientNetV2: Smaller Models and Faster Training","date":"2021-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"szq0214/fkd","path":"FKD/FKD_ViT/SReT.py","file_url":"https://github.com/szq0214/fkd/blob/HEAD/FKD/FKD_ViT/SReT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e3021018c5f52aca","mcp_get_code":{"code_sha256":"e3021018c5f52aca"}},{"arxiv_id":"2103.16302","paper":"/paper/rethinking-spatial-dimensions-of-vision","title":"Rethinking Spatial Dimensions of Vision Transformers","date":"2021-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ahmedelmahy/myownvit","path":"vit_pytorch/pit.py","file_url":"https://github.com/ahmedelmahy/myownvit/blob/HEAD/vit_pytorch/pit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"208dc760722cfcfa","mcp_get_code":{"code_sha256":"208dc760722cfcfa"}},{"arxiv_id":"2103.16302","paper":"/paper/rethinking-spatial-dimensions-of-vision","title":"Rethinking Spatial Dimensions of Vision Transformers","date":"2021-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"conceptofmind/PiT-flax","path":"pit.py","file_url":"https://github.com/conceptofmind/PiT-flax/blob/HEAD/pit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"285deef776e40994","mcp_get_code":{"code_sha256":"285deef776e40994"}},{"arxiv_id":"2103.15808","paper":"/paper/cvt-introducing-convolutions-to-vision","title":"CvT: Introducing Convolutions to Vision Transformers","date":"2021-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ahmedelmahy/myownvit","path":"vit_pytorch/cvt.py","file_url":"https://github.com/ahmedelmahy/myownvit/blob/HEAD/vit_pytorch/cvt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"991c37c831796a95","mcp_get_code":{"code_sha256":"991c37c831796a95"}},{"arxiv_id":"2103.15808","paper":"/paper/cvt-introducing-convolutions-to-vision","title":"CvT: Introducing Convolutions to Vision Transformers","date":"2021-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"conceptofmind/CvT-flax","path":"cvt_flax/cvt_flax.py","file_url":"https://github.com/conceptofmind/CvT-flax/blob/HEAD/cvt_flax/cvt_flax.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"52559df32e30ffb2","mcp_get_code":{"code_sha256":"52559df32e30ffb2"}},{"arxiv_id":"2103.15808","paper":"/paper/cvt-introducing-convolutions-to-vision","title":"CvT: Introducing Convolutions to Vision Transformers","date":"2021-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/esvit","path":"models/cvt_v4_transformer.py","file_url":"https://github.com/microsoft/esvit/blob/HEAD/models/cvt_v4_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"28bc4fb247eda528","mcp_get_code":{"code_sha256":"28bc4fb247eda528"}},{"arxiv_id":"2103.15691","paper":"/paper/2103-15691","title":"ViViT: A Video Vision Transformer","date":"2021-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KSonPham/ViVit-a-Pytorch-implementation","path":"models/modeling.py","file_url":"https://github.com/KSonPham/ViVit-a-Pytorch-implementation/blob/HEAD/models/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9650a9a4002b76d8","mcp_get_code":{"code_sha256":"9650a9a4002b76d8"}},{"arxiv_id":"2103.14899","paper":"/paper/2103-14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","date":"2021-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rishikksh20/CrossViT-pytorch","path":"crossvit.py","file_url":"https://github.com/rishikksh20/CrossViT-pytorch/blob/HEAD/crossvit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"411c4d270072eb2e","mcp_get_code":{"code_sha256":"411c4d270072eb2e"}},{"arxiv_id":"2103.14899","paper":"/paper/2103-14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","date":"2021-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ahmedelmahy/myownvit","path":"vit_pytorch/cross_vit.py","file_url":"https://github.com/ahmedelmahy/myownvit/blob/HEAD/vit_pytorch/cross_vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39b524cdd79f5d2e","mcp_get_code":{"code_sha256":"39b524cdd79f5d2e"}},{"arxiv_id":"2103.14899","paper":"/paper/2103-14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","date":"2021-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"conceptofmind/CrossViT-flax","path":"cross_vit_flax/cross_vit_flax.py","file_url":"https://github.com/conceptofmind/CrossViT-flax/blob/HEAD/cross_vit_flax/cross_vit_flax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"695e0238d8d29d65","mcp_get_code":{"code_sha256":"695e0238d8d29d65"}},{"arxiv_id":"2103.12091","paper":"/paper/transformers-solve-the-limited-receptive","title":"Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction","date":"2021-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ygjwd12345/TransDepth","path":"pytorch/TransUNet/networks/vit_seg_modeling.py","file_url":"https://github.com/ygjwd12345/TransDepth/blob/HEAD/pytorch/TransUNet/networks/vit_seg_modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c8230155e056fdde","mcp_get_code":{"code_sha256":"c8230155e056fdde"}},{"arxiv_id":"2103.11816","paper":"/paper/incorporating-convolution-designs-into-visual","title":"Incorporating Convolution Designs into Visual Transformers","date":"2021-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"coeusguo/ceit","path":"ceit_model.py","file_url":"https://github.com/coeusguo/ceit/blob/HEAD/ceit_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"88ac331124a64a60","mcp_get_code":{"code_sha256":"88ac331124a64a60"}},{"arxiv_id":"2103.10455","paper":"/paper/3d-human-pose-estimation-with-spatial-and","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","date":"2021-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thuxyz19/test","path":"common/model_poseformer.py","file_url":"https://github.com/thuxyz19/test/blob/HEAD/common/model_poseformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fab27d0fb962f729","mcp_get_code":{"code_sha256":"fab27d0fb962f729"}},{"arxiv_id":"2103.06818","paper":"/paper/coming-down-to-earth-satellite-to-street-view","title":"Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization","date":"2021-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aysim/comingdowntoearth","path":"networks/c_gan.py","file_url":"https://github.com/aysim/comingdowntoearth/blob/HEAD/networks/c_gan.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2452bfc25a290e18","mcp_get_code":{"code_sha256":"2452bfc25a290e18"}},{"arxiv_id":"2103.03206","paper":"/paper/perceiver-general-perception-with-iterative","title":"Perceiver: General Perception with Iterative Attention","date":"2021-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Rishit-dagli/Perceiver","path":"perceiver/perceiver.py","file_url":"https://github.com/Rishit-dagli/Perceiver/blob/HEAD/perceiver/perceiver.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2b6160b81f7900b0","mcp_get_code":{"code_sha256":"2b6160b81f7900b0"}},{"arxiv_id":"2103.03206","paper":"/paper/perceiver-general-perception-with-iterative","title":"Perceiver: General Perception with Iterative Attention","date":"2021-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/perceiver-pytorch","path":"perceiver_pytorch/perceiver_pytorch.py","file_url":"https://github.com/lucidrains/perceiver-pytorch/blob/HEAD/perceiver_pytorch/perceiver_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1f325569b6d0c2df","mcp_get_code":{"code_sha256":"1f325569b6d0c2df"}},{"arxiv_id":"2103.03206","paper":"/paper/perceiver-general-perception-with-iterative","title":"Perceiver: General Perception with Iterative Attention","date":"2021-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kietngt00/hmdb51-recognition","path":"model/attention.py","file_url":"https://github.com/kietngt00/hmdb51-recognition/blob/HEAD/model/attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"407c9004f3d03831","mcp_get_code":{"code_sha256":"407c9004f3d03831"}},{"arxiv_id":"2103.03206","paper":"/paper/perceiver-general-perception-with-iterative","title":"Perceiver: General Perception with Iterative Attention","date":"2021-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sooheon/perceiver-jax","path":"perceiver_jax/perceiver_jax.py","file_url":"https://github.com/sooheon/perceiver-jax/blob/HEAD/perceiver_jax/perceiver_jax.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9a7903b6b454a21a","mcp_get_code":{"code_sha256":"9a7903b6b454a21a"}},{"arxiv_id":"2103.03206","paper":"/paper/perceiver-general-perception-with-iterative","title":"Perceiver: General Perception with Iterative Attention","date":"2021-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fac2003/perceiver-multi-modality-pytorch","path":"perceiver_pytorch/perceiver_pytorch.py","file_url":"https://github.com/fac2003/perceiver-multi-modality-pytorch/blob/HEAD/perceiver_pytorch/perceiver_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b908a940626ba009","mcp_get_code":{"code_sha256":"b908a940626ba009"}},{"arxiv_id":"2103.03206","paper":"/paper/perceiver-general-perception-with-iterative","title":"Perceiver: General Perception with Iterative Attention","date":"2021-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Xianchao-Wu/perceiver-pytorch","path":"perceiver_pytorch/perceiver_pytorch.py","file_url":"https://github.com/Xianchao-Wu/perceiver-pytorch/blob/HEAD/perceiver_pytorch/perceiver_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dab3a202eec902f5","mcp_get_code":{"code_sha256":"dab3a202eec902f5"}},{"arxiv_id":"2103.03206","paper":"/paper/perceiver-general-perception-with-iterative","title":"Perceiver: General Perception with Iterative Attention","date":"2021-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clementpoiret/Perceiver_MNIST","path":"utils/perceiver.py","file_url":"https://github.com/clementpoiret/Perceiver_MNIST/blob/HEAD/utils/perceiver.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c78772b126a7d1bf","mcp_get_code":{"code_sha256":"c78772b126a7d1bf"}},{"arxiv_id":"2103.01209","paper":"/paper/generative-adversarial-transformers","title":"Generative Adversarial Transformers","date":"2021-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/transganformer","path":"transganformer/transganformer.py","file_url":"https://github.com/lucidrains/transganformer/blob/HEAD/transganformer/transganformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"82e38a4ffe03866d","mcp_get_code":{"code_sha256":"82e38a4ffe03866d"}},{"arxiv_id":"2103.00112","paper":"/paper/transformer-in-transformer","title":"Transformer in Transformer","date":"2021-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huawei-noah/CV-Backbones","path":"tnt_pytorch/tnt.py","file_url":"https://github.com/huawei-noah/CV-Backbones/blob/HEAD/tnt_pytorch/tnt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aa47e20b1de49f21","mcp_get_code":{"code_sha256":"aa47e20b1de49f21"}},{"arxiv_id":"2103.00112","paper":"/paper/transformer-in-transformer","title":"Transformer in Transformer","date":"2021-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Rishit-dagli/Transformer-in-Transformer","path":"tnt/tnt.py","file_url":"https://github.com/Rishit-dagli/Transformer-in-Transformer/blob/HEAD/tnt/tnt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ae43efde4f9bdb00","mcp_get_code":{"code_sha256":"ae43efde4f9bdb00"}},{"arxiv_id":"2103.00112","paper":"/paper/transformer-in-transformer","title":"Transformer in Transformer","date":"2021-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/transformer-in-transformer","path":"transformer_in_transformer/tnt.py","file_url":"https://github.com/lucidrains/transformer-in-transformer/blob/HEAD/transformer_in_transformer/tnt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"81188c67ea536d0b","mcp_get_code":{"code_sha256":"81188c67ea536d0b"}},{"arxiv_id":"2102.12122","paper":"/paper/pyramid-vision-transformer-a-versatile","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","date":"2021-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DarshanDeshpande/jax-models","path":"jax_models/models/pvit.py","file_url":"https://github.com/DarshanDeshpande/jax-models/blob/HEAD/jax_models/models/pvit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"07fdb7e2bfa01afa","mcp_get_code":{"code_sha256":"07fdb7e2bfa01afa"}},{"arxiv_id":"2102.12122","paper":"/paper/pyramid-vision-transformer-a-versatile","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","date":"2021-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"whai362/PVT","path":"classification/pvt.py","file_url":"https://github.com/whai362/PVT/blob/HEAD/classification/pvt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5dada1aeda7932eb","mcp_get_code":{"code_sha256":"5dada1aeda7932eb"}},{"arxiv_id":"2102.12122","paper":"/paper/pyramid-vision-transformer-a-versatile","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","date":"2021-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/vision-longformer","path":"src/models/msvit.py","file_url":"https://github.com/microsoft/vision-longformer/blob/HEAD/src/models/msvit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"592e8438de425b53","mcp_get_code":{"code_sha256":"592e8438de425b53"}},{"arxiv_id":"2102.06696","paper":"/paper/efficient-conditional-gan-transfer-with","title":"Efficient Conditional GAN Transfer with Knowledge Propagation across Classes","date":"2021-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mshahbazi72/cGANTransfer","path":"BigGAN.py","file_url":"https://github.com/mshahbazi72/cGANTransfer/blob/HEAD/BigGAN.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e0e75705a765d4fb","mcp_get_code":{"code_sha256":"e0e75705a765d4fb"}},{"arxiv_id":"2102.05095","paper":"/paper/is-space-time-attention-all-you-need-for","title":"Is Space-Time Attention All You Need for Video Understanding?","date":"2021-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"halixness/generative_timesformer_pytorch","path":"timesformer_pytorch/timesformer_pytorch.py","file_url":"https://github.com/halixness/generative_timesformer_pytorch/blob/HEAD/timesformer_pytorch/timesformer_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9e6eb12055d4b5db","mcp_get_code":{"code_sha256":"9e6eb12055d4b5db"}},{"arxiv_id":"2102.05095","paper":"/paper/is-space-time-attention-all-you-need-for","title":"Is Space-Time Attention All You Need for Video Understanding?","date":"2021-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/TimeSformer-pytorch","path":"timesformer_pytorch/timesformer_pytorch.py","file_url":"https://github.com/lucidrains/TimeSformer-pytorch/blob/HEAD/timesformer_pytorch/timesformer_pytorch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f7e0694aefe90304","mcp_get_code":{"code_sha256":"f7e0694aefe90304"}},{"arxiv_id":"2102.04990","paper":"/paper/sg2caps-revisiting-scene-graphs-for-image","title":"In Defense of Scene Graphs for Image Captioning","date":"2021-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kien085/sg2caps","path":"models/AttModel_mem4.py","file_url":"https://github.com/kien085/sg2caps/blob/HEAD/models/AttModel_mem4.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"262edaef058c9fc5","mcp_get_code":{"code_sha256":"262edaef058c9fc5"}},{"arxiv_id":"2102.02973","paper":"/paper/show-attend-and-distill-knowledge","title":"Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching","date":"2021-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clovaai/attention-feature-distillation","path":"distill/AFD.py","file_url":"https://github.com/clovaai/attention-feature-distillation/blob/HEAD/distill/AFD.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"44c8fee3462b48ea","mcp_get_code":{"code_sha256":"44c8fee3462b48ea"}},{"arxiv_id":"2101.11986","paper":"/paper/tokens-to-token-vit-training-vision","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","date":"2021-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ttt496/vit-pytorch","path":"vit_pytorch/t2t.py","file_url":"https://github.com/ttt496/vit-pytorch/blob/HEAD/vit_pytorch/t2t.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"26b673d7f271bb3d","mcp_get_code":{"code_sha256":"26b673d7f271bb3d"}},{"arxiv_id":"2101.11986","paper":"/paper/tokens-to-token-vit-training-vision","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","date":"2021-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"conceptofmind/Token-to-Token-ViT-flax","path":"t2t.py","file_url":"https://github.com/conceptofmind/Token-to-Token-ViT-flax/blob/HEAD/t2t.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c5be8ba345dd9a2b","mcp_get_code":{"code_sha256":"c5be8ba345dd9a2b"}},{"arxiv_id":"2101.11986","paper":"/paper/tokens-to-token-vit-training-vision","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","date":"2021-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yitu-opensource/T2T-ViT","path":"models/t2t_vit.py","file_url":"https://github.com/yitu-opensource/T2T-ViT/blob/HEAD/models/t2t_vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"bb63e3aa0e13762e","mcp_get_code":{"code_sha256":"bb63e3aa0e13762e"}},{"arxiv_id":"2101.11986","paper":"/paper/tokens-to-token-vit-training-vision","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","date":"2021-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tianhai123/vit-pytorch","path":"vit_pytorch/t2t.py","file_url":"https://github.com/tianhai123/vit-pytorch/blob/HEAD/vit_pytorch/t2t.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6f1ffa7354716396","mcp_get_code":{"code_sha256":"6f1ffa7354716396"}},{"arxiv_id":"2101.11605","paper":"/paper/bottleneck-transformers-for-visual","title":"Bottleneck Transformers for Visual Recognition","date":"2021-01-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/bottleneck-transformer-pytorch","path":"bottleneck_transformer_pytorch/bottleneck_transformer_pytorch.py","file_url":"https://github.com/lucidrains/bottleneck-transformer-pytorch/blob/HEAD/bottleneck_transformer_pytorch/bottleneck_transformer_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1ee91139c3f9ceb2","mcp_get_code":{"code_sha256":"1ee91139c3f9ceb2"}},{"arxiv_id":"2012.12877","paper":"/paper/training-data-efficient-image-transformers","title":"Training data-efficient image transformers & distillation through attention","date":"2020-12-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba/EasyCV","path":"easycv/models/backbones/vision_transformer.py","file_url":"https://github.com/alibaba/EasyCV/blob/HEAD/easycv/models/backbones/vision_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c0bfabc05e380222","mcp_get_code":{"code_sha256":"c0bfabc05e380222"}},{"arxiv_id":"2011.04592","paper":"/paper/generating-image-descriptions-via-sequential","title":"Generating Image Descriptions via Sequential Cross-Modal Alignment Guided by Human Gaze","date":"2020-11-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dmg-illc/didec-seq-gen","path":"description_generation/models/model_pret_gaze_2RNN.py","file_url":"https://github.com/dmg-illc/didec-seq-gen/blob/HEAD/description_generation/models/model_pret_gaze_2RNN.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"685139212826c9d8","mcp_get_code":{"code_sha256":"685139212826c9d8"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mahmoodlab/hipt","path":"HIPT_4K/vision_transformer.py","file_url":"https://github.com/mahmoodlab/hipt/blob/HEAD/HIPT_4K/vision_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"3806102629027da3","mcp_get_code":{"code_sha256":"3806102629027da3"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nachiket273/VisTrans","path":"vistrans/models/vit.py","file_url":"https://github.com/nachiket273/VisTrans/blob/HEAD/vistrans/models/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5f7f49ed28389849","mcp_get_code":{"code_sha256":"5f7f49ed28389849"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"explainingai-code/VIT-Pytorch","path":"model/transformer.py","file_url":"https://github.com/explainingai-code/VIT-Pytorch/blob/HEAD/model/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"998014b6f71af139","mcp_get_code":{"code_sha256":"998014b6f71af139"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nachiket273/Vision_transformer_pytorch","path":"vit.py","file_url":"https://github.com/nachiket273/Vision_transformer_pytorch/blob/HEAD/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4e9b033c45eda05d","mcp_get_code":{"code_sha256":"4e9b033c45eda05d"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OML-Team/open-metric-learning","path":"oml/models/vit_dino/external_v2/vision_transformer.py","file_url":"https://github.com/OML-Team/open-metric-learning/blob/HEAD/oml/models/vit_dino/external_v2/vision_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"49d02e769ff703f2","mcp_get_code":{"code_sha256":"49d02e769ff703f2"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SHI-Labs/Compact-Transformers","path":"src/vit.py","file_url":"https://github.com/SHI-Labs/Compact-Transformers/blob/HEAD/src/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fb209281f7dc7ae4","mcp_get_code":{"code_sha256":"fb209281f7dc7ae4"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HzcIrving/DeepLearning_PlayGround","path":"VIT/Model.py","file_url":"https://github.com/HzcIrving/DeepLearning_PlayGround/blob/HEAD/VIT/Model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e65111831b48a20f","mcp_get_code":{"code_sha256":"e65111831b48a20f"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"meowbutlerdev/ViT","path":"vit.py","file_url":"https://github.com/meowbutlerdev/ViT/blob/HEAD/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"03826c508404de86","mcp_get_code":{"code_sha256":"03826c508404de86"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Mayurji/Image-Classification-PyTorch","path":"ViT.py","file_url":"https://github.com/Mayurji/Image-Classification-PyTorch/blob/HEAD/ViT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"99a27bf8a6745bca","mcp_get_code":{"code_sha256":"99a27bf8a6745bca"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/vit-pytorch","path":"vit_pytorch/vit.py","file_url":"https://github.com/lucidrains/vit-pytorch/blob/HEAD/vit_pytorch/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"303b5fcf0f3b83ab","mcp_get_code":{"code_sha256":"303b5fcf0f3b83ab"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jankrepl/mildlyoverfitted","path":"github_adventures/vision_transformer/custom.py","file_url":"https://github.com/jankrepl/mildlyoverfitted/blob/HEAD/github_adventures/vision_transformer/custom.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e526ae2dd17da9d3","mcp_get_code":{"code_sha256":"e526ae2dd17da9d3"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"skchen1993/TrangFG","path":"models/modeling.py","file_url":"https://github.com/skchen1993/TrangFG/blob/HEAD/models/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4112d886f96a0258","mcp_get_code":{"code_sha256":"4112d886f96a0258"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kamalkraj/Vision-Transformer","path":"model.py","file_url":"https://github.com/kamalkraj/Vision-Transformer/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5dba6c3975d89f90","mcp_get_code":{"code_sha256":"5dba6c3975d89f90"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"asarigun/TransGAN","path":"models.py","file_url":"https://github.com/asarigun/TransGAN/blob/HEAD/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f817c1f38785cb41","mcp_get_code":{"code_sha256":"f817c1f38785cb41"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gnoses/ViT_examples","path":"vit_pytorch.py","file_url":"https://github.com/gnoses/ViT_examples/blob/HEAD/vit_pytorch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c39e7fad73097655","mcp_get_code":{"code_sha256":"c39e7fad73097655"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gupta-abhay/ViT","path":"vit/vit.py","file_url":"https://github.com/gupta-abhay/ViT/blob/HEAD/vit/vit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d42779b90537733","mcp_get_code":{"code_sha256":"8d42779b90537733"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"affjljoo3581/deit3-jax","path":"src/modeling.py","file_url":"https://github.com/affjljoo3581/deit3-jax/blob/HEAD/src/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"565ce60dfb1885d4","mcp_get_code":{"code_sha256":"565ce60dfb1885d4"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"conceptofmind/ViT-haiku","path":"vit.py","file_url":"https://github.com/conceptofmind/ViT-haiku/blob/HEAD/vit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"67e042f60cb0eb8a","mcp_get_code":{"code_sha256":"67e042f60cb0eb8a"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tahmid0007/VisionTransformer","path":"Google_ViT.py","file_url":"https://github.com/tahmid0007/VisionTransformer/blob/HEAD/Google_ViT.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c834ab0929ce55ae","mcp_get_code":{"code_sha256":"c834ab0929ce55ae"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SupreethRao99/VisionTransformer","path":"PyTorch/ViTModel.py","file_url":"https://github.com/SupreethRao99/VisionTransformer/blob/HEAD/PyTorch/ViTModel.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"745db312b8377945","mcp_get_code":{"code_sha256":"745db312b8377945"}},{"arxiv_id":"2010.03276","paper":"/paper/zest-zero-shot-learning-from-text","title":"ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization","date":"2020-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tzuf/ZEST","path":"models.py","file_url":"https://github.com/tzuf/ZEST/blob/HEAD/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d285a51be1b7454c","mcp_get_code":{"code_sha256":"d285a51be1b7454c"}},{"arxiv_id":"2006.11807","paper":"/paper/improving-image-captioning-with-better-use-of-1","title":"Improving Image Captioning with Better Use of Captions","date":"2020-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Gitsamshi/WeakVRD-Captioning","path":"models/VrgModel.py","file_url":"https://github.com/Gitsamshi/WeakVRD-Captioning/blob/HEAD/models/VrgModel.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cbd68ece47fcdc7d","mcp_get_code":{"code_sha256":"cbd68ece47fcdc7d"}},{"arxiv_id":"2006.11239","paper":"/paper/denoising-diffusion-probabilistic-models","title":"Denoising Diffusion Probabilistic Models","date":"2020-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/make-a-video-pytorch","path":"make_a_video_pytorch/make_a_video.py","file_url":"https://github.com/lucidrains/make-a-video-pytorch/blob/HEAD/make_a_video_pytorch/make_a_video.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"727d939a33684dc3","mcp_get_code":{"code_sha256":"727d939a33684dc3"}},{"arxiv_id":"2006.11239","paper":"/paper/denoising-diffusion-probabilistic-models","title":"Denoising Diffusion Probabilistic Models","date":"2020-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yiyixuxu/denoising-diffusion-flax","path":"denoising_diffusion_flax/unet.py","file_url":"https://github.com/yiyixuxu/denoising-diffusion-flax/blob/HEAD/denoising_diffusion_flax/unet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"391c56da8c23eaf6","mcp_get_code":{"code_sha256":"391c56da8c23eaf6"}},{"arxiv_id":"2006.11239","paper":"/paper/denoising-diffusion-probabilistic-models","title":"Denoising Diffusion Probabilistic Models","date":"2020-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cjfghk5697/Pytorch-Research-Paper-Implementations","path":"Diffusion/DDPM/models/model.py","file_url":"https://github.com/cjfghk5697/Pytorch-Research-Paper-Implementations/blob/HEAD/Diffusion/DDPM/models/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"27a0c9621917d719","mcp_get_code":{"code_sha256":"27a0c9621917d719"}},{"arxiv_id":"2006.04558","paper":"/paper/fastspeech-2-fast-and-high-quality-end-to-end","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ndkgit339/fastspeech2-filled_pause_speech_synthesis","path":"model/fastspeech2.py","file_url":"https://github.com/ndkgit339/fastspeech2-filled_pause_speech_synthesis/blob/HEAD/model/fastspeech2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dfedf95397e85d63","mcp_get_code":{"code_sha256":"dfedf95397e85d63"}},{"arxiv_id":"2005.04560","paper":"/paper/posterior-control-of-blackbox-generation","title":"Posterior Control of Blackbox Generation","date":"2020-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FranxYao/Gumbel-CRF","path":"src/modeling/latent_temp_crf_ar.py","file_url":"https://github.com/FranxYao/Gumbel-CRF/blob/HEAD/src/modeling/latent_temp_crf_ar.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"29319ce69524bccb","mcp_get_code":{"code_sha256":"29319ce69524bccb"}},{"arxiv_id":"2002.10389","paper":"/paper/semi-supervised-neural-architecture-search","title":"Semi-Supervised Neural Architecture Search","date":"2020-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"renqianluo/SemiNAS","path":"imagenet/nao_controller.py","file_url":"https://github.com/renqianluo/SemiNAS/blob/HEAD/imagenet/nao_controller.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ab3ae1affca959ef","mcp_get_code":{"code_sha256":"ab3ae1affca959ef"}},{"arxiv_id":"2002.05969","paper":"/paper/query2box-reasoning-over-knowledge-graphs-in-1","title":"Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings","date":"2020-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hyren/query2box","path":"codes/model.py","file_url":"https://github.com/hyren/query2box/blob/HEAD/codes/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2575bb19d82fba6d","mcp_get_code":{"code_sha256":"2575bb19d82fba6d"}},{"arxiv_id":"1909.11942","paper":"/paper/albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kamalkraj/ALBERT-TF2.0","path":"albert.py","file_url":"https://github.com/kamalkraj/ALBERT-TF2.0/blob/HEAD/albert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a8a24272ed7b74f4","mcp_get_code":{"code_sha256":"a8a24272ed7b74f4"}},{"arxiv_id":"1901.02860","paper":"/paper/transformer-xl-attentive-language-models","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","date":"2019-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/code-prediction-transformer","path":"model.py","file_url":"https://github.com/facebookresearch/code-prediction-transformer/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e3217ee8bd314909","mcp_get_code":{"code_sha256":"e3217ee8bd314909"}},{"arxiv_id":"1901.02860","paper":"/paper/transformer-xl-attentive-language-models","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","date":"2019-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opendilab/DI-engine","path":"ding/torch_utils/network/transformer.py","file_url":"https://github.com/opendilab/DI-engine/blob/HEAD/ding/torch_utils/network/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fe3454282cf0b88e","mcp_get_code":{"code_sha256":"fe3454282cf0b88e"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fanchenyou/transformer-study","path":"transformer_bert_from_scratch_5.py","file_url":"https://github.com/fanchenyou/transformer-study/blob/HEAD/transformer_bert_from_scratch_5.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fa24061b6aade569","mcp_get_code":{"code_sha256":"fa24061b6aade569"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huanghonggit/Mask-Language-Model","path":"model/bert.py","file_url":"https://github.com/huanghonggit/Mask-Language-Model/blob/HEAD/model/bert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2f01baa6a2569f01","mcp_get_code":{"code_sha256":"2f01baa6a2569f01"}},{"arxiv_id":"1710.10903","paper":"/paper/graph-attention-networks","title":"Graph Attention Networks","date":"2017-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Aveek-Saha/Graph-Attention-Net","path":"gat.py","file_url":"https://github.com/Aveek-Saha/Graph-Attention-Net/blob/HEAD/gat.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ea7e984b0e2dc3d2","mcp_get_code":{"code_sha256":"ea7e984b0e2dc3d2"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WenYanger/General-Transformer-Pytorch","path":"Transformer.py","file_url":"https://github.com/WenYanger/General-Transformer-Pytorch/blob/HEAD/Transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"98f39b8698a27474","mcp_get_code":{"code_sha256":"98f39b8698a27474"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agentdr1/la_mil","path":"tmil/t_mil.py","file_url":"https://github.com/agentdr1/la_mil/blob/HEAD/tmil/t_mil.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d41d2318721cdae","mcp_get_code":{"code_sha256":"7d41d2318721cdae"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"plkmo/Transformer-Eng2French","path":"src/models.py","file_url":"https://github.com/plkmo/Transformer-Eng2French/blob/HEAD/src/models.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5ac38813dcddad14","mcp_get_code":{"code_sha256":"5ac38813dcddad14"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"graykode/gpt-2-Pytorch","path":"GPT2/model.py","file_url":"https://github.com/graykode/gpt-2-Pytorch/blob/HEAD/GPT2/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"91d76a1548d7d9ca","mcp_get_code":{"code_sha256":"91d76a1548d7d9ca"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fanchenyou/transformer-study","path":"utils/attention.py","file_url":"https://github.com/fanchenyou/transformer-study/blob/HEAD/utils/attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a7153c067c37036d","mcp_get_code":{"code_sha256":"a7153c067c37036d"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kh-kim/simple-nmt","path":"simple_nmt/models/transformer.py","file_url":"https://github.com/kh-kim/simple-nmt/blob/HEAD/simple_nmt/models/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"08b5b32fc8336299","mcp_get_code":{"code_sha256":"08b5b32fc8336299"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"semicontinuity/nlp","path":"lopuhin_transformer_lm/lm/model.py","file_url":"https://github.com/semicontinuity/nlp/blob/HEAD/lopuhin_transformer_lm/lm/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"42fad6e85b79e765","mcp_get_code":{"code_sha256":"42fad6e85b79e765"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"conceptofmind/LaMDA-pytorch","path":"lamda_pytorch/lamda_pytorch.py","file_url":"https://github.com/conceptofmind/LaMDA-pytorch/blob/HEAD/lamda_pytorch/lamda_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9782629b3a308ef0","mcp_get_code":{"code_sha256":"9782629b3a308ef0"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/pytorch-seq2seq","path":"seq2seq/models/attention.py","file_url":"https://github.com/IBM/pytorch-seq2seq/blob/HEAD/seq2seq/models/attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fa5671b3a33ffde3","mcp_get_code":{"code_sha256":"fa5671b3a33ffde3"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BrianPulfer/PapersReimplementations","path":"src/nlp/layers/encoder.py","file_url":"https://github.com/BrianPulfer/PapersReimplementations/blob/HEAD/src/nlp/layers/encoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6f534d51aff2ec87","mcp_get_code":{"code_sha256":"6f534d51aff2ec87"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ShivamRajSharma/Transformer-Architectures-From-Scratch","path":"TRANSFORMERS.py","file_url":"https://github.com/ShivamRajSharma/Transformer-Architectures-From-Scratch/blob/HEAD/TRANSFORMERS.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d12ff40c5428f95","mcp_get_code":{"code_sha256":"8d12ff40c5428f95"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tree-park/transformer_lm","path":"lib/model/transformer.py","file_url":"https://github.com/tree-park/transformer_lm/blob/HEAD/lib/model/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2d7742705ba9eab5","mcp_get_code":{"code_sha256":"2d7742705ba9eab5"}},{"arxiv_id":"1704.04368","paper":"/paper/get-to-the-point-summarization-with-pointer","title":"Get To The Point: Summarization with Pointer-Generator Networks","date":"2017-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiminsun/pointer-generator","path":"models/model.py","file_url":"https://github.com/jiminsun/pointer-generator/blob/HEAD/models/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cc3e0df6c9cadffc","mcp_get_code":{"code_sha256":"cc3e0df6c9cadffc"}},{"arxiv_id":"1704.04368","paper":"/paper/get-to-the-point-summarization-with-pointer","title":"Get To The Point: Summarization with Pointer-Generator Networks","date":"2017-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zide05/pointer-gen-fastnlp","path":"model/model.py","file_url":"https://github.com/zide05/pointer-gen-fastnlp/blob/HEAD/model/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"48ab9258f9be2b31","mcp_get_code":{"code_sha256":"48ab9258f9be2b31"}},{"arxiv_id":"1704.04368","paper":"/paper/get-to-the-point-summarization-with-pointer","title":"Get To The Point: Summarization with Pointer-Generator Networks","date":"2017-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sblayush/summarization","path":"Attention/Attention.py","file_url":"https://github.com/sblayush/summarization/blob/HEAD/Attention/Attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"08757013b9c0d91c","mcp_get_code":{"code_sha256":"08757013b9c0d91c"}},{"arxiv_id":"1609.08144","paper":"/paper/googles-neural-machine-translation-system","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","date":"2016-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kh-kim/simple-nmt","path":"simple_nmt/models/seq2seq.py","file_url":"https://github.com/kh-kim/simple-nmt/blob/HEAD/simple_nmt/models/seq2seq.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"efc311adeb93a786","mcp_get_code":{"code_sha256":"efc311adeb93a786"}},{"arxiv_id":"1609.08144","paper":"/paper/googles-neural-machine-translation-system","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","date":"2016-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZHANG45/multi_gpu_seq2seq","path":"seq2seq2.py","file_url":"https://github.com/ZHANG45/multi_gpu_seq2seq/blob/HEAD/seq2seq2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e60bd6d0b1cb5dc5","mcp_get_code":{"code_sha256":"e60bd6d0b1cb5dc5"}},{"arxiv_id":"1609.07843","paper":"/paper/pointer-sentinel-mixture-models","title":"Pointer Sentinel Mixture Models","date":"2016-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"emanjavacas/pie","path":"pie/models/decoder.py","file_url":"https://github.com/emanjavacas/pie/blob/HEAD/pie/models/decoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"48e865d17f832cf9","mcp_get_code":{"code_sha256":"48e865d17f832cf9"}},{"arxiv_id":"1601.06759","paper":"/paper/pixel-recurrent-neural-networks","title":"Pixel Recurrent Neural Networks","date":"2016-01-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"encoreus/gs-jacobi_for_tarflow","path":"GS_Jacobi_sampling.py","file_url":"https://github.com/encoreus/gs-jacobi_for_tarflow/blob/HEAD/GS_Jacobi_sampling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ee4de74c78e0ecd2","mcp_get_code":{"code_sha256":"ee4de74c78e0ecd2"}},{"arxiv_id":"1601.06759","paper":"/paper/pixel-recurrent-neural-networks","title":"Pixel Recurrent Neural Networks","date":"2016-01-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-tarflow","path":"transformer_flow.py","file_url":"https://github.com/apple/ml-tarflow/blob/HEAD/transformer_flow.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"7eca12f0033fe394","mcp_get_code":{"code_sha256":"7eca12f0033fe394"}},{"arxiv_id":"openreview_AAWlum38oE","paper":null,"title":"arXiv:openreview_AAWlum38oE","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"1202kbs/AYT","path":"src/ayt/unets.py","file_url":"https://github.com/1202kbs/AYT/blob/HEAD/src/ayt/unets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d812fc65fcde81f1","mcp_get_code":{"code_sha256":"d812fc65fcde81f1"}},{"arxiv_id":"ijcai2025_0890","paper":null,"title":"arXiv:ijcai2025_0890","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Auguuust/DiffEC","path":"Diffusion_based/DiffusionModels/noisePredictModels/Unet/_1DUNet.py","file_url":"https://github.com/Auguuust/DiffEC/blob/HEAD/Diffusion_based/DiffusionModels/noisePredictModels/Unet/_1DUNet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b8f691ce52b7d8cb","mcp_get_code":{"code_sha256":"b8f691ce52b7d8cb"}},{"arxiv_id":"aaai_28529","paper":null,"title":"arXiv:aaai_28529","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"AlienZhang1996/S2WAT","path":"model/s2wat.py","file_url":"https://github.com/AlienZhang1996/S2WAT/blob/HEAD/model/s2wat.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"030a8fc94ebdef1d","mcp_get_code":{"code_sha256":"030a8fc94ebdef1d"}},{"arxiv_id":"aaai_28388","paper":null,"title":"arXiv:aaai_28388","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"924973292/TOP-ReID","path":"modeling/fusion_part/CRM.py","file_url":"https://github.com/924973292/TOP-ReID/blob/HEAD/modeling/fusion_part/CRM.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ac5a227badd13252","mcp_get_code":{"code_sha256":"ac5a227badd13252"}},{"arxiv_id":"Zhou_PanoLlama_Generating_Endless_and_Coherent_Panoramas_with_Next-Token-Prediction_LLMs_ICCV_2025_paper","paper":null,"title":"arXiv:Zhou_PanoLlama_Generating_Endless_and_Coherent_Panoramas_with_Next-Token-Prediction_LLMs_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"0606zt/PanoLlama","path":"token_generator/gpt.py","file_url":"https://github.com/0606zt/PanoLlama/blob/HEAD/token_generator/gpt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f9965fbd3d39078f","mcp_get_code":{"code_sha256":"f9965fbd3d39078f"}},{"arxiv_id":"Wang_In2SET_Intra-Inter_Similarity_Exploiting_Transformer_for_Dual-Camera_Compressive_Hyperspectral_Imaging_CVPR_2024_paper","paper":null,"title":"arXiv:Wang_In2SET_Intra-Inter_Similarity_Exploiting_Transformer_for_Dual-Camera_Compressive_Hyperspectral_Imaging_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"2JONAS/In2SET","path":"net.py","file_url":"https://github.com/2JONAS/In2SET/blob/HEAD/net.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c7366098f4a927a5","mcp_get_code":{"code_sha256":"c7366098f4a927a5"}}]}