{"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/mlp-3","entry":"Mlp","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":102,"n_papers_ran":96,"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":108,"n_samples_ran":101,"n_samples_fingerprinted":9,"n_places":108,"n_places_pointer_only":45,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":101,"unverified":7},"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":"2605.05863","paper":"/paper/arxiv-2605-05863","title":"SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"CarloRomeo427/SOPE","path":"src/algos/agent_sope.py","file_url":"https://github.com/CarloRomeo427/SOPE/blob/HEAD/src/algos/agent_sope.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"962e617b40ecd9f5","mcp_get_code":{"code_sha256":"962e617b40ecd9f5"}},{"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":"9acdc39b2a030cb7","mcp_get_code":{"code_sha256":"9acdc39b2a030cb7"}},{"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":"e71525ebf968c4c3","mcp_get_code":{"code_sha256":"e71525ebf968c4c3"}},{"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":"1bd4afb036e3fc07","mcp_get_code":{"code_sha256":"1bd4afb036e3fc07"}},{"arxiv_id":"2602.05387","paper":"/paper/arxiv-2602-05387","title":"Parallel Swin Transformer-Enhanced 3D MRI-to-CT Synthesis for MRI-Only Radiotherapy Planning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"mobaidoctor/med2transformer","path":"utils.py","file_url":"https://github.com/mobaidoctor/med2transformer/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"81bedfe71b98da1d","mcp_get_code":{"code_sha256":"81bedfe71b98da1d"}},{"arxiv_id":"2602.00490","paper":"/paper/arxiv-2602-00490","title":"HSSDCT: Factorized Spatial-Spectral Correlation for Hyperspectral Image Fusion","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"jemmyleee/HSSDCT","path":"models/hssdct.py","file_url":"https://github.com/jemmyleee/HSSDCT/blob/HEAD/models/hssdct.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1ca91bbffeb129c6","mcp_get_code":{"code_sha256":"1ca91bbffeb129c6"}},{"arxiv_id":"2601.16631","paper":"/paper/arxiv-2601-16631","title":"PanopMamba: Vision State Space Modeling for Nuclei Panoptic Segmentation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"mkang315/PanopMamba","path":"mmseg/models/backbones/msvssm.py","file_url":"https://github.com/mkang315/PanopMamba/blob/HEAD/mmseg/models/backbones/msvssm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"65c1e05eec0dfce5","mcp_get_code":{"code_sha256":"65c1e05eec0dfce5"}},{"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":"6210361c8db8ce59","mcp_get_code":{"code_sha256":"6210361c8db8ce59"}},{"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":"131a8f7d31012a1a","mcp_get_code":{"code_sha256":"131a8f7d31012a1a"}},{"arxiv_id":"2507.00880","paper":null,"title":"arXiv:2507.00880","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"XuRuihan/NNFormer","path":"neuralformer/models/encoders/neuralformer.py","file_url":"https://github.com/XuRuihan/NNFormer/blob/HEAD/neuralformer/models/encoders/neuralformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"11f7eb41a99440ee","mcp_get_code":{"code_sha256":"11f7eb41a99440ee"}},{"arxiv_id":"2506.18463","paper":"/paper/dip-unsupervised-dense-in-context-post","title":"DIP: Unsupervised Dense In-Context Post-training of Visual Representations","date":"2025-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sirkosophia/dip","path":"models/dipnet.py","file_url":"https://github.com/sirkosophia/dip/blob/HEAD/models/dipnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"d8c583f1cc12d333","mcp_get_code":{"code_sha256":"d8c583f1cc12d333"}},{"arxiv_id":"2506.02408","paper":"/paper/revisiting-end-to-end-learning-with-slide","title":"Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology","date":"2025-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dearcaat/e2e-wsi-abmilx","path":"modules/abmilx.py","file_url":"https://github.com/dearcaat/e2e-wsi-abmilx/blob/HEAD/modules/abmilx.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"590b24e96b73fc6d","mcp_get_code":{"code_sha256":"590b24e96b73fc6d"}},{"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":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"779f838cdd4a5df6","mcp_get_code":{"code_sha256":"779f838cdd4a5df6"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7e045c902914c785","mcp_get_code":{"code_sha256":"7e045c902914c785"}},{"arxiv_id":"2503.13147","paper":"/paper/iterative-predictor-critic-code-decoding-for","title":"Iterative Predictor-Critic Code Decoding for Real-World Image Dehazing","date":"2025-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jiayi-Fu/IPC-Dehaze","path":"basicsr/archs/dehazeToken_arch.py","file_url":"https://github.com/Jiayi-Fu/IPC-Dehaze/blob/HEAD/basicsr/archs/dehazeToken_arch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"8e2c391fd64aed64","mcp_get_code":{"code_sha256":"8e2c391fd64aed64"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8fb31e08ee3391a7","mcp_get_code":{"code_sha256":"8fb31e08ee3391a7"}},{"arxiv_id":"2503.03965","paper":"/paper/all-atom-diffusion-transformers-unified","title":"All-atom Diffusion Transformers: Unified generative modelling of molecules and materials","date":"2025-03-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/all-atom-diffusion-transformer","path":"src/models/denoisers/dit.py","file_url":"https://github.com/facebookresearch/all-atom-diffusion-transformer/blob/HEAD/src/models/denoisers/dit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"0694baedef001ec2","mcp_get_code":{"code_sha256":"0694baedef001ec2"}},{"arxiv_id":"2503.00986","paper":"/paper/modeling-fine-grained-hand-object-dynamics","title":"Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning","date":"2025-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openrobotlab/egohod","path":"model/timesformer.py","file_url":"https://github.com/openrobotlab/egohod/blob/HEAD/model/timesformer.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":"aa37ee515d967134","mcp_get_code":{"code_sha256":"aa37ee515d967134"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"64a1f9d86e5a825a","mcp_get_code":{"code_sha256":"64a1f9d86e5a825a"}},{"arxiv_id":"2502.16025","paper":"/paper/featsharp-your-vision-model-features-sharper","title":"FeatSharp: Your Vision Model Features, Sharper","date":"2025-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nvlabs/radio","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f4144fb782c06f3e","mcp_get_code":{"code_sha256":"f4144fb782c06f3e"}},{"arxiv_id":"2502.11663","paper":"/paper/maskgwm-a-generalizable-driving-world-model","title":"MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction","date":"2025-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SenseTime-FVG/OpenDWM","path":"src/dwm/models/mask_layers.py","file_url":"https://github.com/SenseTime-FVG/OpenDWM/blob/HEAD/src/dwm/models/mask_layers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d95c624cec119af3","mcp_get_code":{"code_sha256":"d95c624cec119af3"}},{"arxiv_id":"2502.02538","paper":"/paper/flow-q-learning","title":"Flow Q-Learning","date":"2025-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MohammadrezaNakhaei/FQL","path":"fql.py","file_url":"https://github.com/MohammadrezaNakhaei/FQL/blob/HEAD/fql.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a6b7c2c470100719","mcp_get_code":{"code_sha256":"a6b7c2c470100719"}},{"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":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"0498c7765ac40058","mcp_get_code":{"code_sha256":"0498c7765ac40058"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"36d5cca2b16c5d54","mcp_get_code":{"code_sha256":"36d5cca2b16c5d54"}},{"arxiv_id":"2412.12095","paper":"/paper/causal-diffusion-transformers-for-generative","title":"Causal Diffusion Transformers for Generative Modeling","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"causalfusion/causalfusion","path":"models.py","file_url":"https://github.com/causalfusion/causalfusion/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":"853c1fff1fdf9ee8","mcp_get_code":{"code_sha256":"853c1fff1fdf9ee8"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3a08e0b2bc5ced4b","mcp_get_code":{"code_sha256":"3a08e0b2bc5ced4b"}},{"arxiv_id":"2407.09842","paper":"/paper/eliminating-feature-ambiguity-for-few-shot","title":"Eliminating Feature Ambiguity for Few-Shot Segmentation","date":"2024-07-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Sam1224/AENet","path":"SCCAN_CyCTR/model/cyc_transformer_plus.py","file_url":"https://github.com/Sam1224/AENet/blob/HEAD/SCCAN_CyCTR/model/cyc_transformer_plus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"130d72a3eeda8859","mcp_get_code":{"code_sha256":"130d72a3eeda8859"}},{"arxiv_id":"2407.04619","paper":"/paper/countgd-multi-modal-open-world-counting","title":"CountGD: Multi-Modal Open-World Counting","date":"2024-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"niki-amini-naieni/countx","path":"models_counting_network.py","file_url":"https://github.com/niki-amini-naieni/countx/blob/HEAD/models_counting_network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6f6aa7aeb7d08957","mcp_get_code":{"code_sha256":"6f6aa7aeb7d08957"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0cde8e101baaac37","mcp_get_code":{"code_sha256":"0cde8e101baaac37"}},{"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":"2cfea2de6e135773","mcp_get_code":{"code_sha256":"2cfea2de6e135773"}},{"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":"335a33f331dc2ff7","mcp_get_code":{"code_sha256":"335a33f331dc2ff7"}},{"arxiv_id":"2405.14527","paper":"/paper/archesweather-an-efficient-ai-weather","title":"ArchesWeather: An efficient AI weather forecasting model at 1.5° resolution","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gcouairon/archesweather","path":"backbones/archesweather.py","file_url":"https://github.com/gcouairon/archesweather/blob/HEAD/backbones/archesweather.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bf1c8663374ad548","mcp_get_code":{"code_sha256":"bf1c8663374ad548"}},{"arxiv_id":"2404.01740","paper":"/paper/weakly-supervised-audio-separation-via-bi","title":"Weakly-supervised Audio Separation via Bi-modal Semantic Similarity","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/bimodalaudioseparation","path":"models/cond_unet_attn.py","file_url":"https://github.com/microsoft/bimodalaudioseparation/blob/HEAD/models/cond_unet_attn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"033bf6b0228555c7","mcp_get_code":{"code_sha256":"033bf6b0228555c7"}},{"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":"3e8438d23c4ccbd4","mcp_get_code":{"code_sha256":"3e8438d23c4ccbd4"}},{"arxiv_id":"2403.07347","paper":"/paper/frequency-decoupling-for-motion-magnification","title":"Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jiafei127/FD4MM","path":"magnet_FD4MM.py","file_url":"https://github.com/Jiafei127/FD4MM/blob/HEAD/magnet_FD4MM.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"97cc636e2d3de32c","mcp_get_code":{"code_sha256":"97cc636e2d3de32c"}},{"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":"a5dd5f3730a5fb22","mcp_get_code":{"code_sha256":"a5dd5f3730a5fb22"}},{"arxiv_id":"2403.01105","paper":"/paper/depth-information-assisted-collaborative","title":"Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing","date":"2024-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhoushen1/DCMPNet","path":"models/DIACMPN.py","file_url":"https://github.com/zhoushen1/DCMPNet/blob/HEAD/models/DIACMPN.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"77b034476886713d","mcp_get_code":{"code_sha256":"77b034476886713d"}},{"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":"62fd73bae3c2a68d","mcp_get_code":{"code_sha256":"62fd73bae3c2a68d"}},{"arxiv_id":"2402.15648","paper":"/paper/mambair-a-simple-baseline-for-image","title":"MambaIR: A Simple Baseline for Image Restoration with State-Space Model","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iridescentttt/SynQT","path":"synqt.py","file_url":"https://github.com/iridescentttt/SynQT/blob/HEAD/synqt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cef8b4a7bdc3ecd8","mcp_get_code":{"code_sha256":"cef8b4a7bdc3ecd8"}},{"arxiv_id":"2402.12138","paper":"/paper/perceiving-longer-sequences-with-bi","title":"Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mrkshllr/bixt","path":"timm/models/bixt.py","file_url":"https://github.com/mrkshllr/bixt/blob/HEAD/timm/models/bixt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"fa167a84fdd9edea","mcp_get_code":{"code_sha256":"fa167a84fdd9edea"}},{"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":"b684a3f5d798d30a","mcp_get_code":{"code_sha256":"b684a3f5d798d30a"}},{"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":"fb956c775e434a63","mcp_get_code":{"code_sha256":"fb956c775e434a63"}},{"arxiv_id":"2309.13700","paper":"/paper/video-adverse-weather-component-suppression","title":"Video Adverse-Weather-Component Suppression Network via Weather Messenger and Adversarial Backpropagation","date":"2023-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"scott-yjyang/ViWS-Net","path":"modeling/model.py","file_url":"https://github.com/scott-yjyang/ViWS-Net/blob/HEAD/modeling/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"848137dc4a2cfd57","mcp_get_code":{"code_sha256":"848137dc4a2cfd57"}},{"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":"6048703a72836ea7","mcp_get_code":{"code_sha256":"6048703a72836ea7"}},{"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":"394b5fd507e86c97","mcp_get_code":{"code_sha256":"394b5fd507e86c97"}},{"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":"78d5aec68b3b3810","mcp_get_code":{"code_sha256":"78d5aec68b3b3810"}},{"arxiv_id":"2308.09891","paper":"/paper/swinlstm-improving-spatiotemporal-prediction","title":"SwinLSTM:Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM","date":"2023-08-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SongTang-x/SwinLSTM","path":"SwinLSTM_B.py","file_url":"https://github.com/SongTang-x/SwinLSTM/blob/HEAD/SwinLSTM_B.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"de345690ecacb912","mcp_get_code":{"code_sha256":"de345690ecacb912"}},{"arxiv_id":"2307.11458","paper":"/paper/strip-mlp-efficient-token-interaction-for","title":"Strip-MLP: Efficient Token Interaction for Vision MLP","date":"2023-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"med-process/strip_mlp","path":"models/strip_mlp.py","file_url":"https://github.com/med-process/strip_mlp/blob/HEAD/models/strip_mlp.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"031e0b19f8c99de7","mcp_get_code":{"code_sha256":"031e0b19f8c99de7"}},{"arxiv_id":"2306.15794","paper":"/paper/hyenadna-long-range-genomic-sequence-modeling","title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","date":"2023-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"frederikkemarin/bend","path":"bend/models/hyena_dna.py","file_url":"https://github.com/frederikkemarin/bend/blob/HEAD/bend/models/hyena_dna.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":"d86ea40df8708d4d","mcp_get_code":{"code_sha256":"d86ea40df8708d4d"}},{"arxiv_id":"2306.07957","paper":"/paper/hidden-biases-of-end-to-end-driving-models","title":"Hidden Biases of End-to-End Driving Models","date":"2023-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"autonomousvision/carla_garage","path":"team_code/transfuser.py","file_url":"https://github.com/autonomousvision/carla_garage/blob/HEAD/team_code/transfuser.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3d4489efff0d96f9","mcp_get_code":{"code_sha256":"3d4489efff0d96f9"}},{"arxiv_id":"2306.06189","paper":"/paper/fastervit-fast-vision-transformers-with","title":"FasterViT: Fast Vision Transformers with Hierarchical Attention","date":"2023-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVlabs/FasterViT","path":"fastervit/models/faster_vit.py","file_url":"https://github.com/NVlabs/FasterViT/blob/HEAD/fastervit/models/faster_vit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"128ed4df18554274","mcp_get_code":{"code_sha256":"128ed4df18554274"}},{"arxiv_id":"2304.07221","paper":"/paper/instance-aware-dynamic-prompt-tuning-for-pre","title":"Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models","date":"2023-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zyh16143998882/IDPT","path":"models/Point_MAE.py","file_url":"https://github.com/zyh16143998882/IDPT/blob/HEAD/models/Point_MAE.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cc1832f8e8b3aa69","mcp_get_code":{"code_sha256":"cc1832f8e8b3aa69"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"11ea568c90b9f65a","mcp_get_code":{"code_sha256":"11ea568c90b9f65a"}},{"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":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a5b98a91fdfc68fa","mcp_get_code":{"code_sha256":"a5b98a91fdfc68fa"}},{"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":"a1715055832f71fd","mcp_get_code":{"code_sha256":"a1715055832f71fd"}},{"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":"c8e94306d07ea4db","mcp_get_code":{"code_sha256":"c8e94306d07ea4db"}},{"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":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"86db5e5160400425","mcp_get_code":{"code_sha256":"86db5e5160400425"}},{"arxiv_id":"2303.15446","paper":"/paper/swiftformer-efficient-additive-attention-for","title":"SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications","date":"2023-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amshaker/swiftformer","path":"models/swiftformer.py","file_url":"https://github.com/amshaker/swiftformer/blob/HEAD/models/swiftformer.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":"2dc33d1c31b0ba12","mcp_get_code":{"code_sha256":"2dc33d1c31b0ba12"}},{"arxiv_id":"2303.15322","paper":"/paper/progressive-semantic-visual-mutual-adaption","title":"Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning","date":"2023-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ManLiuCoder/PSVMA","path":"models/modeling/PSVMAModel/PSVMANet.py","file_url":"https://github.com/ManLiuCoder/PSVMA/blob/HEAD/models/modeling/PSVMAModel/PSVMANet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"37fda41f5c65d130","mcp_get_code":{"code_sha256":"37fda41f5c65d130"}},{"arxiv_id":"2303.11126","paper":"/paper/robustifying-token-attention-for-vision","title":"Robustifying Token Attention for Vision Transformers","date":"2023-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guoyongcs/TAPADL","path":"TAPADL_FAN/models/tap_fan.py","file_url":"https://github.com/guoyongcs/TAPADL/blob/HEAD/TAPADL_FAN/models/tap_fan.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2c0905736daa9f4b","mcp_get_code":{"code_sha256":"2c0905736daa9f4b"}},{"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":"ed4c1d521a7e03a2","mcp_get_code":{"code_sha256":"ed4c1d521a7e03a2"}},{"arxiv_id":"2303.07180","paper":"/paper/incomplete-multi-view-multi-label-learning","title":"Incomplete Multi-View Multi-Label Learning via Label-Guided Masked View- and Category-Aware Transformers","date":"2023-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"justsmart/LMVCAT","path":"model.py","file_url":"https://github.com/justsmart/LMVCAT/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"04e76ed6e0b45088","mcp_get_code":{"code_sha256":"04e76ed6e0b45088"}},{"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/mmif-emma","path":"nets/Ufuser.py","file_url":"https://github.com/zhaozixiang1228/mmif-emma/blob/HEAD/nets/Ufuser.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d41e29922999d7fa","mcp_get_code":{"code_sha256":"d41e29922999d7fa"}},{"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/mmif-cddfuse","path":"net.py","file_url":"https://github.com/zhaozixiang1228/mmif-cddfuse/blob/HEAD/net.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dc2b3fa6c2ac9333","mcp_get_code":{"code_sha256":"dc2b3fa6c2ac9333"}},{"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":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ab28cb15a9f42269","mcp_get_code":{"code_sha256":"ab28cb15a9f42269"}},{"arxiv_id":"2303.00440","paper":"/paper/extracting-motion-and-appearance-via-inter","title":"Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation","date":"2023-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MCG-NJU/EMA-VFI","path":"model/feature_extractor.py","file_url":"https://github.com/MCG-NJU/EMA-VFI/blob/HEAD/model/feature_extractor.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":"49e7751169736ead","mcp_get_code":{"code_sha256":"49e7751169736ead"}},{"arxiv_id":"2302.10414","paper":"/paper/improving-scene-text-image-super-resolution","title":"Improving Scene Text Image Super-resolution via Dual Prior Modulation Network","date":"2023-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jdfxzzy/DPMN","path":"model/pgrm.py","file_url":"https://github.com/jdfxzzy/DPMN/blob/HEAD/model/pgrm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2eda70dc4bda97b3","mcp_get_code":{"code_sha256":"2eda70dc4bda97b3"}},{"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":"c68e980b6461aa93","mcp_get_code":{"code_sha256":"c68e980b6461aa93"}},{"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":"001c4e1dde23a54e","mcp_get_code":{"code_sha256":"001c4e1dde23a54e"}},{"arxiv_id":"2209.15200","paper":"/paper/an-efficient-encoder-decoder-architecture","title":"An efficient encoder-decoder architecture with top-down attention for speech separation","date":"2022-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JusperLee/TDANet","path":"look2hear/models/TDANet.py","file_url":"https://github.com/JusperLee/TDANet/blob/HEAD/look2hear/models/TDANet.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":"c3b7c4dad2d1de89","mcp_get_code":{"code_sha256":"c3b7c4dad2d1de89"}},{"arxiv_id":"2208.03792","paper":"/paper/domain-randomization-enhanced-depth","title":"Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects","date":"2022-08-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PKU-EPIC/DREDS","path":"CatePoseEstimation/networks/SwinDRNet.py","file_url":"https://github.com/PKU-EPIC/DREDS/blob/HEAD/CatePoseEstimation/networks/SwinDRNet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ab49e7dfb4c6af7e","mcp_get_code":{"code_sha256":"ab49e7dfb4c6af7e"}},{"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":"170eeb3ae2272801","mcp_get_code":{"code_sha256":"170eeb3ae2272801"}},{"arxiv_id":"2206.09959","paper":"/paper/global-context-vision-transformers","title":"Global Context Vision Transformers","date":"2022-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nvlabs/gcvit","path":"models/gc_vit.py","file_url":"https://github.com/nvlabs/gcvit/blob/HEAD/models/gc_vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"54d976068690d3d1","mcp_get_code":{"code_sha256":"54d976068690d3d1"}},{"arxiv_id":"2206.09959","paper":"/paper/global-context-vision-transformers","title":"Global Context Vision Transformers","date":"2022-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"awsaf49/gcvit-tf","path":"gcvit/models/gcvit.py","file_url":"https://github.com/awsaf49/gcvit-tf/blob/HEAD/gcvit/models/gcvit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"175f4b05a6f94cf8","mcp_get_code":{"code_sha256":"175f4b05a6f94cf8"}},{"arxiv_id":"2206.06801","paper":"/paper/peripheral-vision-transformer","title":"Peripheral Vision Transformer","date":"2022-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"juhongm999/pervit","path":"model/pervit.py","file_url":"https://github.com/juhongm999/pervit/blob/HEAD/model/pervit.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":"7c8acca47b6cad85","mcp_get_code":{"code_sha256":"7c8acca47b6cad85"}},{"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":"150e9a8b4f87d226","mcp_get_code":{"code_sha256":"150e9a8b4f87d226"}},{"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":"e18d4ea8b6351e78","mcp_get_code":{"code_sha256":"e18d4ea8b6351e78"}},{"arxiv_id":"2204.03645","paper":"/paper/davit-dual-attention-vision-transformers","title":"DaViT: Dual Attention Vision Transformers","date":"2022-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dingmyu/davit","path":"timm/models/davit.py","file_url":"https://github.com/dingmyu/davit/blob/HEAD/timm/models/davit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c1395a46164d140a","mcp_get_code":{"code_sha256":"c1395a46164d140a"}},{"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":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f3cd14e6c18a60d8","mcp_get_code":{"code_sha256":"f3cd14e6c18a60d8"}},{"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":"526bd04b3cf88443","mcp_get_code":{"code_sha256":"526bd04b3cf88443"}},{"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":"heekhero/DTL","path":"classification/models/swin_transformer.py","file_url":"https://github.com/heekhero/DTL/blob/HEAD/classification/models/swin_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"22e33235319249df","mcp_get_code":{"code_sha256":"22e33235319249df"}},{"arxiv_id":"2203.10209","paper":"/paper/swintextspotter-scene-text-spotting-via","title":"SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition","date":"2022-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jacobtyo/swintextspotter","path":"projects/SWINTS/swints/FocalTransformer.py","file_url":"https://github.com/jacobtyo/swintextspotter/blob/HEAD/projects/SWINTS/swints/FocalTransformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6bb9db10893a2dc5","mcp_get_code":{"code_sha256":"6bb9db10893a2dc5"}},{"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":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3215e1b62b114566","mcp_get_code":{"code_sha256":"3215e1b62b114566"}},{"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":"d1243176e8bb4111","mcp_get_code":{"code_sha256":"d1243176e8bb4111"}},{"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":"5a8382845c81cc22","mcp_get_code":{"code_sha256":"5a8382845c81cc22"}},{"arxiv_id":"2201.10801","paper":"/paper/when-shift-operation-meets-vision-transformer","title":"When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism","date":"2022-01-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/SPACH","path":"models/shiftvit.py","file_url":"https://github.com/microsoft/SPACH/blob/HEAD/models/shiftvit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eb2bb570ac51f183","mcp_get_code":{"code_sha256":"eb2bb570ac51f183"}},{"arxiv_id":"2201.04850","paper":"/paper/bridgeformer-bridging-video-text-retrieval","title":"Bridging Video-text Retrieval with Multiple Choice Questions","date":"2022-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"towhee-io/towhee","path":"towhee/models/bridgeformer/bridge_former_training_block.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/bridgeformer/bridge_former_training_block.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":"cbf3c6f7dca35838","mcp_get_code":{"code_sha256":"cbf3c6f7dca35838"}},{"arxiv_id":"2201.04676","paper":"/paper/uniformer-unified-transformer-for-efficient-1","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","date":"2022-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"towhee-io/towhee","path":"towhee/models/uniformer/uniformer.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/uniformer/uniformer.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":"865f8893e93aa461","mcp_get_code":{"code_sha256":"865f8893e93aa461"}},{"arxiv_id":"2201.03545","paper":"/paper/a-convnet-for-the-2020s","title":"A ConvNet for the 2020s","date":"2022-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SarthakYadav/audax","path":"audax/models/convnext.py","file_url":"https://github.com/SarthakYadav/audax/blob/HEAD/audax/models/convnext.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"baad12607c91ab0b","mcp_get_code":{"code_sha256":"baad12607c91ab0b"}},{"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":"FlyEgle/MAE-pytorch","path":"model/Transformers/VIT/mae.py","file_url":"https://github.com/FlyEgle/MAE-pytorch/blob/HEAD/model/Transformers/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":"e8f3808093706645","mcp_get_code":{"code_sha256":"e8f3808093706645"}},{"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":"c64c51e855184f53","mcp_get_code":{"code_sha256":"c64c51e855184f53"}},{"arxiv_id":"2110.02034","paper":"/paper/dropout-q-functions-for-doubly-efficient","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","date":"2021-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"watchernyu/REDQ","path":"redq/algos/redq_sac.py","file_url":"https://github.com/watchernyu/REDQ/blob/HEAD/redq/algos/redq_sac.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ec1489c1ccfeec3","mcp_get_code":{"code_sha256":"3ec1489c1ccfeec3"}},{"arxiv_id":"2108.10257","paper":"/paper/swinir-image-restoration-using-swin","title":"SwinIR: Image Restoration Using Swin Transformer","date":"2021-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pilot7747/sldl","path":"sldl/image/swinir.py","file_url":"https://github.com/pilot7747/sldl/blob/HEAD/sldl/image/swinir.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":"9b7e99667d6f97b5","mcp_get_code":{"code_sha256":"9b7e99667d6f97b5"}},{"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":"635ca5ddeb4973f7","mcp_get_code":{"code_sha256":"635ca5ddeb4973f7"}},{"arxiv_id":"2104.11227","paper":"/paper/multiscale-vision-transformers","title":"Multiscale Vision Transformers","date":"2021-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"towhee-io/towhee","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.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":"9220e80dfcec043a","mcp_get_code":{"code_sha256":"9220e80dfcec043a"}},{"arxiv_id":"2104.06399","paper":"/paper/co-scale-conv-attentional-image-transformers","title":"Co-Scale Conv-Attentional Image Transformers","date":"2021-04-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlpc-ucsd/CoaT","path":"src/models/coat.py","file_url":"https://github.com/mlpc-ucsd/CoaT/blob/HEAD/src/models/coat.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":"0b841fb406f1acc4","mcp_get_code":{"code_sha256":"0b841fb406f1acc4"}},{"arxiv_id":"2104.06399","paper":"/paper/co-scale-conv-attentional-image-transformers","title":"Co-Scale Conv-Attentional Image Transformers","date":"2021-04-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver-ai/vidt","path":"methods/coat_w_ram.py","file_url":"https://github.com/naver-ai/vidt/blob/HEAD/methods/coat_w_ram.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":"829106170239b59a","mcp_get_code":{"code_sha256":"829106170239b59a"}},{"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":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"35965045e79a53f5","mcp_get_code":{"code_sha256":"35965045e79a53f5"}},{"arxiv_id":"2103.14030","paper":"/paper/swin-transformer-hierarchical-vision","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","date":"2021-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Burf/tfdetection","path":"tfdet/model/backbone/swin_transformer.py","file_url":"https://github.com/Burf/tfdetection/blob/HEAD/tfdet/model/backbone/swin_transformer.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":"ead0d8b596c9c2fb","mcp_get_code":{"code_sha256":"ead0d8b596c9c2fb"}},{"arxiv_id":"2103.14030","paper":"/paper/swin-transformer-hierarchical-vision","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","date":"2021-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yingkaisha/keras-vision-transformer","path":"keras_vision_transformer/swin_layers.py","file_url":"https://github.com/yingkaisha/keras-vision-transformer/blob/HEAD/keras_vision_transformer/swin_layers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7dbba99d6a7f3858","mcp_get_code":{"code_sha256":"7dbba99d6a7f3858"}},{"arxiv_id":"2103.14030","paper":"/paper/swin-transformer-hierarchical-vision","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","date":"2021-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rishigami/Swin-Transformer-TF","path":"swintransformer/model.py","file_url":"https://github.com/rishigami/Swin-Transformer-TF/blob/HEAD/swintransformer/model.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":"70df6b2fcc3c66c8","mcp_get_code":{"code_sha256":"70df6b2fcc3c66c8"}},{"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":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c359fa03063baf48","mcp_get_code":{"code_sha256":"c359fa03063baf48"}},{"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":"m-bain/video-transformers","path":"video-transformers/timesformer.py","file_url":"https://github.com/m-bain/video-transformers/blob/HEAD/video-transformers/timesformer.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":"409ab4896697a02f","mcp_get_code":{"code_sha256":"409ab4896697a02f"}},{"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":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"64505a0b6aa5e3d4","mcp_get_code":{"code_sha256":"64505a0b6aa5e3d4"}},{"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":"117f497351823aa8","mcp_get_code":{"code_sha256":"117f497351823aa8"}},{"arxiv_id":"1707.06347","paper":"/paper/proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ASzot/ppo-pytorch","path":"model.py","file_url":"https://github.com/ASzot/ppo-pytorch/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"088783306dda80fe","mcp_get_code":{"code_sha256":"088783306dda80fe"}},{"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":"HzcIrving/DeepLearning_PlayGround","path":"Swin-Transformer/Model.py","file_url":"https://github.com/HzcIrving/DeepLearning_PlayGround/blob/HEAD/Swin-Transformer/Model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e25662fe99653409","mcp_get_code":{"code_sha256":"e25662fe99653409"}},{"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":"a7f875372934db0c","mcp_get_code":{"code_sha256":"a7f875372934db0c"}}]}