{"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/droppath","entry":"DropPath","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":75,"n_papers_ran":73,"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":89,"n_samples_ran":84,"n_samples_fingerprinted":72,"n_places":89,"n_places_pointer_only":36,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":84,"unverified":5},"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":"2608.22619","paper":"/paper/arxiv-2608-22619","title":"GET: Generative Embedding Translation for Medical Image Segmentation","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"maklachur/GET","path":"networks/embedding_translation.py","file_url":"https://github.com/maklachur/GET/blob/HEAD/networks/embedding_translation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6970a40ad31697f9","mcp_get_code":{"code_sha256":"6970a40ad31697f9"}},{"arxiv_id":"2606.14222","paper":"/paper/arxiv-2606-14222","title":"Learning the Context of Errors: Black-Box Online Adaptation of Time Series Foundation Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Fifthky/ORCA","path":"core/refiner_attn.py","file_url":"https://github.com/Fifthky/ORCA/blob/HEAD/core/refiner_attn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ea28ec451a5d07bc","mcp_get_code":{"code_sha256":"ea28ec451a5d07bc"}},{"arxiv_id":"2606.05116","paper":"/paper/arxiv-2606-05116","title":"Graph Set Transformer","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"daenuprobst/gst-conference","path":"src/graph_set_transformer/models/gst.py","file_url":"https://github.com/daenuprobst/gst-conference/blob/HEAD/src/graph_set_transformer/models/gst.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8d650e598e1402c8","mcp_get_code":{"code_sha256":"8d650e598e1402c8"}},{"arxiv_id":"2605.25127","paper":"/paper/arxiv-2605-25127","title":"PQDT: Pseudo-Query Dual Transformer for Robust Point Cloud Restoration","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"ins-uni-bonn/PQDT","path":"pqdt/models/pq_transformer.py","file_url":"https://github.com/ins-uni-bonn/PQDT/blob/HEAD/pqdt/models/pq_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ae51a68c68f169d8","mcp_get_code":{"code_sha256":"ae51a68c68f169d8"}},{"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":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"52ab34ca8fd2e134","mcp_get_code":{"code_sha256":"52ab34ca8fd2e134"}},{"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":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ea7880551588ee9f","mcp_get_code":{"code_sha256":"ea7880551588ee9f"}},{"arxiv_id":"2602.22555","paper":"/paper/arxiv-2602-22555","title":"Autoregressive Visual Decoding from EEG Signals","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"ddicee/avde","path":"models/labram.py","file_url":"https://github.com/ddicee/avde/blob/HEAD/models/labram.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"84590d675e94d536","mcp_get_code":{"code_sha256":"84590d675e94d536"}},{"arxiv_id":"2602.21421","paper":"/paper/arxiv-2602-21421","title":"ECHOSAT: Estimating Canopy Height Over Space and Time","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"ai4forest/echosat","path":"fine-tuning/models/swin_video_unet.py","file_url":"https://github.com/ai4forest/echosat/blob/HEAD/fine-tuning/models/swin_video_unet.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":"bdfb44252c4a4200","mcp_get_code":{"code_sha256":"bdfb44252c4a4200"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96592475595fbed1","mcp_get_code":{"code_sha256":"96592475595fbed1"}},{"arxiv_id":"2602.19113","paper":"/paper/arxiv-2602-19113","title":"Learning from Complexity: Exploring Dynamic Sample Pruning of Spatio-Temporal Training","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"HKUDS/OpenCity","path":"model/OpenCity/OpenCity.py","file_url":"https://github.com/HKUDS/OpenCity/blob/HEAD/model/OpenCity/OpenCity.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dbb44455f4f7cf38","mcp_get_code":{"code_sha256":"dbb44455f4f7cf38"}},{"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":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8c1361edd265ca8a","mcp_get_code":{"code_sha256":"8c1361edd265ca8a"}},{"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":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"367c364be6605f4c","mcp_get_code":{"code_sha256":"367c364be6605f4c"}},{"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":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8e464eea7a15e985","mcp_get_code":{"code_sha256":"8e464eea7a15e985"}},{"arxiv_id":"2601.06793","paper":"/paper/arxiv-2601-06793","title":"CliffordNet: All You Need is Geometric Algebra","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"ParaMind2025/CAN","path":"model.py","file_url":"https://github.com/ParaMind2025/CAN/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2a0ce6ede68d0fc3","mcp_get_code":{"code_sha256":"2a0ce6ede68d0fc3"}},{"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":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9e7503f9df29310e","mcp_get_code":{"code_sha256":"9e7503f9df29310e"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"862cf06383f8bde7","mcp_get_code":{"code_sha256":"862cf06383f8bde7"}},{"arxiv_id":"2505.24103","paper":"/paper/weakly-supervised-affordance-grounding-guided","title":"Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors","date":"2025-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"woyut/wsag-plsp","path":"codes/models/decoder_affordance.py","file_url":"https://github.com/woyut/wsag-plsp/blob/HEAD/codes/models/decoder_affordance.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7bf42bf0e6458cb1","mcp_get_code":{"code_sha256":"7bf42bf0e6458cb1"}},{"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":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b7e965b5c4fbf144","mcp_get_code":{"code_sha256":"b7e965b5c4fbf144"}},{"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":"4d93211cfa9bdffc","mcp_get_code":{"code_sha256":"4d93211cfa9bdffc"}},{"arxiv_id":"2503.15141","paper":null,"title":"arXiv:2503.15141","date":null,"month_inferred_from_arxiv_id":"2025-03","title_source":null,"repo":"djukicn/ocebo","path":"models/ocebo.py","file_url":"https://github.com/djukicn/ocebo/blob/HEAD/models/ocebo.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":"15090130e3a1e904","mcp_get_code":{"code_sha256":"15090130e3a1e904"}},{"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":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e8fe59329c1a7b8a","mcp_get_code":{"code_sha256":"e8fe59329c1a7b8a"}},{"arxiv_id":"2503.09402","paper":"/paper/vlog-video-language-models-by-generative","title":"VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary","date":"2025-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"showlab/VLog","path":"VLog/model/models.py","file_url":"https://github.com/showlab/VLog/blob/HEAD/VLog/model/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"eb3438f3ff649ddf","mcp_get_code":{"code_sha256":"eb3438f3ff649ddf"}},{"arxiv_id":"2502.03549","paper":"/paper/kronecker-mask-and-interpretive-prompts-are","title":"Kronecker Mask and Interpretive Prompts are Language-Action Video Learners","date":"2025-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yjyddq/CLAVER","path":"models/claver.py","file_url":"https://github.com/yjyddq/CLAVER/blob/HEAD/models/claver.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"02c3d66d7386b4ce","mcp_get_code":{"code_sha256":"02c3d66d7386b4ce"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"76f9e42efc0d4711","mcp_get_code":{"code_sha256":"76f9e42efc0d4711"}},{"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":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59c07cf4d49e5e3c","mcp_get_code":{"code_sha256":"59c07cf4d49e5e3c"}},{"arxiv_id":"2407.02309","paper":"/paper/semantically-guided-representation-learning","title":"Semantically Guided Representation Learning For Action Anticipation","date":"2024-07-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ADiko1997/S-GEAR","path":"models/base_model_ts.py","file_url":"https://github.com/ADiko1997/S-GEAR/blob/HEAD/models/base_model_ts.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":"f4388cc6db5bce14","mcp_get_code":{"code_sha256":"f4388cc6db5bce14"}},{"arxiv_id":"2406.04303","paper":"/paper/vision-lstm-xlstm-as-generic-vision-backbone","title":"Vision-LSTM: xLSTM as Generic Vision Backbone","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NX-AI/vision-lstm","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.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":"5fa540c6a1346171","mcp_get_code":{"code_sha256":"5fa540c6a1346171"}},{"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":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"07bed269ee55adea","mcp_get_code":{"code_sha256":"07bed269ee55adea"}},{"arxiv_id":"2404.08472","paper":"/paper/tslanet-rethinking-transformers-for-time","title":"TSLANet: Rethinking Transformers for Time Series Representation Learning","date":"2024-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WenjieDu/PyPOTS","path":"pypots/nn/modules/tslanet/backbone.py","file_url":"https://github.com/WenjieDu/PyPOTS/blob/HEAD/pypots/nn/modules/tslanet/backbone.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"43c44182d498a36d","mcp_get_code":{"code_sha256":"43c44182d498a36d"}},{"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":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"7d9a8a01e3d8b2af","mcp_get_code":{"code_sha256":"7d9a8a01e3d8b2af"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"938eafe395be5d19","mcp_get_code":{"code_sha256":"938eafe395be5d19"}},{"arxiv_id":"2403.15139","paper":"/paper/deep-generative-model-based-rate-distortion","title":"Deep Generative Model based Rate-Distortion for Image Downscaling Assessment","date":"2024-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IIGROUP/MANIQA","path":"models/maniqa.py","file_url":"https://github.com/IIGROUP/MANIQA/blob/HEAD/models/maniqa.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":"93f0fde3bc773068","mcp_get_code":{"code_sha256":"93f0fde3bc773068"}},{"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":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"59f48e4236839efb","mcp_get_code":{"code_sha256":"59f48e4236839efb"}},{"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":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2b3233292ba7ed4f","mcp_get_code":{"code_sha256":"2b3233292ba7ed4f"}},{"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":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0e191e0cd5b78fae","mcp_get_code":{"code_sha256":"0e191e0cd5b78fae"}},{"arxiv_id":"2308.13494","paper":"/paper/eventful-transformers-leveraging-temporal","title":"Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers","date":"2023-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WISION-Lab/eventful-transformer","path":"eventful_transformer/blocks.py","file_url":"https://github.com/WISION-Lab/eventful-transformer/blob/HEAD/eventful_transformer/blocks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f70a7b357e415e5e","mcp_get_code":{"code_sha256":"f70a7b357e415e5e"}},{"arxiv_id":"2307.14008","paper":"/paper/adaptive-frequency-filters-as-efficient","title":"Adaptive Frequency Filters As Efficient Global Token Mixers","date":"2023-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NWPU-Li/AFFNet","path":"aff_block_LL.py","file_url":"https://github.com/NWPU-Li/AFFNet/blob/HEAD/aff_block_LL.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"99f368d7aea9ef52","mcp_get_code":{"code_sha256":"99f368d7aea9ef52"}},{"arxiv_id":"2304.08451","paper":"/paper/efficient-video-action-detection-with-token","title":"Efficient Video Action Detection with Token Dropout and Context Refinement","date":"2023-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MCG-NJU/EVAD","path":"projects/evad/models/vit_model.py","file_url":"https://github.com/MCG-NJU/EVAD/blob/HEAD/projects/evad/models/vit_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f1ba368c5af15b64","mcp_get_code":{"code_sha256":"f1ba368c5af15b64"}},{"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":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"22e81d05c408426c","mcp_get_code":{"code_sha256":"22e81d05c408426c"}},{"arxiv_id":"2304.03435","paper":"/paper/towards-unified-scene-text-spotting-based-on","title":"Towards Unified Scene Text Spotting based on Sequence Generation","date":"2023-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clovaai/units","path":"units/models/model.py","file_url":"https://github.com/clovaai/units/blob/HEAD/units/models/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":"2dfdf4c6074881e3","mcp_get_code":{"code_sha256":"2dfdf4c6074881e3"}},{"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":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e6e9f6bf7f63ce5e","mcp_get_code":{"code_sha256":"e6e9f6bf7f63ce5e"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"81da177eaf52ee01","mcp_get_code":{"code_sha256":"81da177eaf52ee01"}},{"arxiv_id":"2303.05194","paper":"/paper/contrastive-model-adaptation-for-cross","title":"Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation","date":"2023-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brdav/cma","path":"models/model.py","file_url":"https://github.com/brdav/cma/blob/HEAD/models/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a6b6a8722e93e121","mcp_get_code":{"code_sha256":"a6b6a8722e93e121"}},{"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":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"43b361f444ae05e1","mcp_get_code":{"code_sha256":"43b361f444ae05e1"}},{"arxiv_id":"2301.10100","paper":"/paper/using-a-waffle-iron-for-automotive-point","title":"Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation","date":"2023-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"valeoai/WaffleIron","path":"waffleiron/backbone.py","file_url":"https://github.com/valeoai/WaffleIron/blob/HEAD/waffleiron/backbone.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e058da1955e6f991","mcp_get_code":{"code_sha256":"e058da1955e6f991"}},{"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":"google-research/pix2seq","path":"architectures/transformers.py","file_url":"https://github.com/google-research/pix2seq/blob/HEAD/architectures/transformers.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":"80161ca59f374d2a","mcp_get_code":{"code_sha256":"80161ca59f374d2a"}},{"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":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"99b1932affbf5fdf","mcp_get_code":{"code_sha256":"99b1932affbf5fdf"}},{"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":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"511f72cb4c20504a","mcp_get_code":{"code_sha256":"511f72cb4c20504a"}},{"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":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a8aec28fef3b8a76","mcp_get_code":{"code_sha256":"a8aec28fef3b8a76"}},{"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":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cb662ef431014eb8","mcp_get_code":{"code_sha256":"cb662ef431014eb8"}},{"arxiv_id":"2205.14209","paper":"/paper/stargraph-a-coarse-to-fine-representation","title":"StarGraph: Knowledge Representation Learning based on Incomplete Two-hop Subgraph","date":"2022-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hzli-ucas/stargraph","path":"model.py","file_url":"https://github.com/hzli-ucas/stargraph/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f3aa96e814dfeea9","mcp_get_code":{"code_sha256":"f3aa96e814dfeea9"}},{"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":"deterministic","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"cd0e7be073ad785f","mcp_get_code":{"code_sha256":"cd0e7be073ad785f"}},{"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":"JunkyByte/easy_ViTPose","path":"easy_ViTPose/vit_models/model.py","file_url":"https://github.com/JunkyByte/easy_ViTPose/blob/HEAD/easy_ViTPose/vit_models/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":"bcec6a4434dcfdb8","mcp_get_code":{"code_sha256":"bcec6a4434dcfdb8"}},{"arxiv_id":"2203.16896","paper":"/paper/craft-cross-attentional-flow-transformer-for","title":"CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow","date":"2022-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"askerlee/craft","path":"core/setrans.py","file_url":"https://github.com/askerlee/craft/blob/HEAD/core/setrans.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"WTFPL","inline_ok":false,"code_sha256_prefix":"691dde70dfd8362b","mcp_get_code":{"code_sha256":"691dde70dfd8362b"}},{"arxiv_id":"2203.15350","paper":"/paper/end-to-end-transformer-based-model-for-image","title":"End-to-End Transformer Based Model for Image Captioning","date":"2022-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jchenghu/expansionnet_v2","path":"models/End_ExpansionNet_v2.py","file_url":"https://github.com/jchenghu/expansionnet_v2/blob/HEAD/models/End_ExpansionNet_v2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d14d5773d2c8e320","mcp_get_code":{"code_sha256":"d14d5773d2c8e320"}},{"arxiv_id":"2203.11589","paper":"/paper/adaptive-patch-exiting-for-scalable-single","title":"Adaptive Patch Exiting for Scalable Single Image Super-Resolution","date":"2022-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"littlepure2333/APE","path":"model/swinir_ape.py","file_url":"https://github.com/littlepure2333/APE/blob/HEAD/model/swinir_ape.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2c28ad5498af1d70","mcp_get_code":{"code_sha256":"2c28ad5498af1d70"}},{"arxiv_id":"2203.11335","paper":"/paper/global-matching-with-overlapping-attention","title":"Global Matching with Overlapping Attention for Optical Flow Estimation","date":"2022-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaofeng94/gmflownet","path":"core/gmflownet_model.py","file_url":"https://github.com/xiaofeng94/gmflownet/blob/HEAD/core/gmflownet_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b20207e9c582c326","mcp_get_code":{"code_sha256":"b20207e9c582c326"}},{"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":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8f059bf3db11537b","mcp_get_code":{"code_sha256":"8f059bf3db11537b"}},{"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":"murufeng/awesome_lightweight_networks","path":"light_cnns/Transformer/ConvNeXt.py","file_url":"https://github.com/murufeng/awesome_lightweight_networks/blob/HEAD/light_cnns/Transformer/ConvNeXt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6255e860ca403ee6","mcp_get_code":{"code_sha256":"6255e860ca403ee6"}},{"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":"DarshanDeshpande/jax-models","path":"jax_models/models/convnext.py","file_url":"https://github.com/DarshanDeshpande/jax-models/blob/HEAD/jax_models/models/convnext.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":"983cc65c35c3d898","mcp_get_code":{"code_sha256":"983cc65c35c3d898"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"0c184b9cfad87e20","mcp_get_code":{"code_sha256":"0c184b9cfad87e20"}},{"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":"a84a5b2f271cf15c","mcp_get_code":{"code_sha256":"a84a5b2f271cf15c"}},{"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":"BUPT-PRIV/MAE-priv","path":"mae/modeling_pretrain.py","file_url":"https://github.com/BUPT-PRIV/MAE-priv/blob/HEAD/mae/modeling_pretrain.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"762514af1d1eeb94","mcp_get_code":{"code_sha256":"762514af1d1eeb94"}},{"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":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8b3435b073f323ec","mcp_get_code":{"code_sha256":"8b3435b073f323ec"}},{"arxiv_id":"2106.08254","paper":"/paper/beit-bert-pre-training-of-image-transformers","title":"BEiT: BERT Pre-Training of Image Transformers","date":"2021-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/vissl","path":"vissl/models/trunks/beit_transformer.py","file_url":"https://github.com/facebookresearch/vissl/blob/HEAD/vissl/models/trunks/beit_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f4d723c4060a9c88","mcp_get_code":{"code_sha256":"f4d723c4060a9c88"}},{"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":"dc3ea9f/RegionViT","path":"models/region_vit.py","file_url":"https://github.com/dc3ea9f/RegionViT/blob/HEAD/models/region_vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"67186f084bc62090","mcp_get_code":{"code_sha256":"67186f084bc62090"}},{"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":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4b04a139b83d832e","mcp_get_code":{"code_sha256":"4b04a139b83d832e"}},{"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":"DarshanDeshpande/jax-models","path":"jax_models/models/segformer.py","file_url":"https://github.com/DarshanDeshpande/jax-models/blob/HEAD/jax_models/models/segformer.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":"8085cbc641b30993","mcp_get_code":{"code_sha256":"8085cbc641b30993"}},{"arxiv_id":"2105.14432","paper":"/paper/transformer-based-deep-image-matching-for","title":"TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification","date":"2021-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JDAI-CV/fast-reid","path":"fastreid/modeling/backbones/vision_transformer.py","file_url":"https://github.com/JDAI-CV/fast-reid/blob/HEAD/fastreid/modeling/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":"75f5c156267fccbd","mcp_get_code":{"code_sha256":"75f5c156267fccbd"}},{"arxiv_id":"2105.01601","paper":"/paper/mlp-mixer-an-all-mlp-architecture-for-vision","title":"MLP-Mixer: An all-MLP Architecture for Vision","date":"2021-05-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"martinsbruveris/tensorflow-image-models","path":"tfimm/architectures/mlp_mixer.py","file_url":"https://github.com/martinsbruveris/tensorflow-image-models/blob/HEAD/tfimm/architectures/mlp_mixer.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":"d011b7b14c9b2500","mcp_get_code":{"code_sha256":"d011b7b14c9b2500"}},{"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":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8eadaa524165fa27","mcp_get_code":{"code_sha256":"8eadaa524165fa27"}},{"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":"shkarupa-alex/tfswin","path":"tfswin/model.py","file_url":"https://github.com/shkarupa-alex/tfswin/blob/HEAD/tfswin/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0a6db98075e5a32","mcp_get_code":{"code_sha256":"c0a6db98075e5a32"}},{"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":"innat/VideoSwin","path":"videoswin/blocks/swin_transformer.py","file_url":"https://github.com/innat/VideoSwin/blob/HEAD/videoswin/blocks/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":"889677dfb48a1e7a","mcp_get_code":{"code_sha256":"889677dfb48a1e7a"}},{"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":"1f71103e68295350","mcp_get_code":{"code_sha256":"1f71103e68295350"}},{"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":"innat/HybridModel-GradCAM","path":"layers/swin_blocks.py","file_url":"https://github.com/innat/HybridModel-GradCAM/blob/HEAD/layers/swin_blocks.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":"5bcf14becf4f18ba","mcp_get_code":{"code_sha256":"5bcf14becf4f18ba"}},{"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":"yangyangxu0/demt","path":"src/model/backbones/swin.py","file_url":"https://github.com/yangyangxu0/demt/blob/HEAD/src/model/backbones/swin.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"89aae91283eb968d","mcp_get_code":{"code_sha256":"89aae91283eb968d"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0fda0888f3c18df0","mcp_get_code":{"code_sha256":"0fda0888f3c18df0"}},{"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":"DarshanDeshpande/jax-models","path":"jax_models/models/swin_transformer.py","file_url":"https://github.com/DarshanDeshpande/jax-models/blob/HEAD/jax_models/models/swin_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":"0267e8763dbcd8ad","mcp_get_code":{"code_sha256":"0267e8763dbcd8ad"}},{"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":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c713760d26bf0a45","mcp_get_code":{"code_sha256":"c713760d26bf0a45"}},{"arxiv_id":"2011.10566","paper":"/paper/exploring-simple-siamese-representation","title":"Exploring Simple Siamese Representation Learning","date":"2020-11-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/clip-rocket","path":"models.py","file_url":"https://github.com/facebookresearch/clip-rocket/blob/HEAD/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"6bd663b5be82dccd","mcp_get_code":{"code_sha256":"6bd663b5be82dccd"}},{"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":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ad5f80b54573c0e0","mcp_get_code":{"code_sha256":"ad5f80b54573c0e0"}},{"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":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1d3ee770ca7b30c9","mcp_get_code":{"code_sha256":"1d3ee770ca7b30c9"}},{"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":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e96ac00ca379ee0e","mcp_get_code":{"code_sha256":"e96ac00ca379ee0e"}},{"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":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fd903c745e98dffd","mcp_get_code":{"code_sha256":"fd903c745e98dffd"}},{"arxiv_id":"1603.09382","paper":"/paper/deep-networks-with-stochastic-depth","title":"Deep Networks with Stochastic Depth","date":"2016-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nachiket273/pytorch_resnet_rs","path":"model/base.py","file_url":"https://github.com/nachiket273/pytorch_resnet_rs/blob/HEAD/model/base.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bd6c794dd7be5c10","mcp_get_code":{"code_sha256":"bd6c794dd7be5c10"}},{"arxiv_id":"1603.09382","paper":"/paper/deep-networks-with-stochastic-depth","title":"Deep Networks with Stochastic Depth","date":"2016-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DarshanDeshpande/jax-models","path":"jax_models/layers/drop.py","file_url":"https://github.com/DarshanDeshpande/jax-models/blob/HEAD/jax_models/layers/drop.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":"7e0f6db857f04fb0","mcp_get_code":{"code_sha256":"7e0f6db857f04fb0"}},{"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":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7d33ccdf4bdeadbf","mcp_get_code":{"code_sha256":"7d33ccdf4bdeadbf"}},{"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":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cb0614ea84e3c9e8","mcp_get_code":{"code_sha256":"cb0614ea84e3c9e8"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1e7c67ed5e41cb0d","mcp_get_code":{"code_sha256":"1e7c67ed5e41cb0d"}}]}