{"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/drop-path","entry":"drop_path","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":325,"n_papers_ran":283,"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":68,"n_samples_ran":42,"n_samples_fingerprinted":17,"n_places":333,"n_places_pointer_only":106,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":29,"ran":13,"unverified":26},"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":"2608.31029","paper":"/paper/arxiv-2608-31029","title":"Driving on Memory","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"boschresearch/MemoryDrivoR","path":"bench2drive/navsim/agents/drivoR/timm_layers.py","file_url":"https://github.com/boschresearch/MemoryDrivoR/blob/HEAD/bench2drive/navsim/agents/drivoR/timm_layers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"68b7ffb36f0515ff","mcp_get_code":{"code_sha256":"68b7ffb36f0515ff"}},{"arxiv_id":"2606.15751","paper":"/paper/arxiv-2606-15751","title":"Acoustic Prompting via Stage-wise Modulation for Few-Shot Learning in Audio Language Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"hyebin-c/aspl","path":"pengi/models/htsat.py","file_url":"https://github.com/hyebin-c/aspl/blob/HEAD/pengi/models/htsat.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2606.11500","paper":"/paper/arxiv-2606-11500","title":"FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"OneMore1/FlexiBrain","path":"flexibrain/models/transformer_block.py","file_url":"https://github.com/OneMore1/FlexiBrain/blob/HEAD/flexibrain/models/transformer_block.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"4bfe3da8a35995ea","mcp_get_code":{"code_sha256":"4bfe3da8a35995ea"}},{"arxiv_id":"2605.30107","paper":"/paper/arxiv-2605-30107","title":"Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"LAION-AI/CLAP","path":"src/laion_clap/clap_module/htsat.py","file_url":"https://github.com/LAION-AI/CLAP/blob/HEAD/src/laion_clap/clap_module/htsat.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2605.12138","paper":"/paper/arxiv-2605-12138","title":"Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"JD-GenX/Uni-AdGen","path":"PBS_metrics/model/vision_transformer.py","file_url":"https://github.com/JD-GenX/Uni-AdGen/blob/HEAD/PBS_metrics/model/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2604.21450","paper":"/paper/arxiv-2604-21450","title":"VARestorer: One-Step VAR Distillation for Real-World Image Super-Resolution","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"EternalEvan/VARestorer","path":"infinity/models/helpers.py","file_url":"https://github.com/EternalEvan/VARestorer/blob/HEAD/infinity/models/helpers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"arxiv_id":"2603.25687","paper":"/paper/arxiv-2603-25687","title":"On Neural Scaling Laws for Weather Emulation through Continual Training","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"ShashankSubramanian/neural-scaling-weather","path":"models/timm_helpers.py","file_url":"https://github.com/ShashankSubramanian/neural-scaling-weather/blob/HEAD/models/timm_helpers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"1c864612eb3b612b","mcp_get_code":{"code_sha256":"1c864612eb3b612b"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"aea279a2d78d1352","mcp_get_code":{"code_sha256":"aea279a2d78d1352"}},{"arxiv_id":"2603.05116","paper":"/paper/arxiv-2603-05116","title":"FedBCGD: Communication-Efficient Accelerated Block Coordinate Gradient Descent for Federated Learning","date":"2026-03-05","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"junkangLiu0/FedBCGD","path":"vit_model.py","file_url":"https://github.com/junkangLiu0/FedBCGD/blob/HEAD/vit_model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fe7d4321dbeef661","mcp_get_code":{"code_sha256":"fe7d4321dbeef661"}},{"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":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"9bdf2492c6e0a8de","mcp_get_code":{"code_sha256":"9bdf2492c6e0a8de"}},{"arxiv_id":"2602.01951","paper":"/paper/arxiv-2602-01951","title":"Enabling Progressive Whole-slide Image Analysis with Multi-scale Pyramidal Network","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"mahmoodlab/HIPT","path":"HIPT_4K/vision_transformer.py","file_url":"https://github.com/mahmoodlab/HIPT/blob/HEAD/HIPT_4K/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2601.21159","paper":"/paper/arxiv-2601-21159","title":"Spatial-Regularization-Aware Dual-Branch Collaborative Inference for Training-Free OVSS in Remote Sensing Imagery","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"yu-ni1989/SDCI","path":"modified_clip/vision_transformer.py","file_url":"https://github.com/yu-ni1989/SDCI/blob/HEAD/modified_clip/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2601.12079","paper":"/paper/arxiv-2601-12079","title":"EmoLat: Text-driven Image Sentiment Transfer via Emotion Latent Space","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"JingVIPLab/EmoLat","path":"model/ViT_helper.py","file_url":"https://github.com/JingVIPLab/EmoLat/blob/HEAD/model/ViT_helper.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2601.07293","paper":"/paper/arxiv-2601-07293","title":"Inference-Time Scaling for Visual AutoRegressive modeling by Searching Representative Samples","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"WD7ang/VAR-Scaling","path":"VAR-main/models/helpers.py","file_url":"https://github.com/WD7ang/VAR-Scaling/blob/HEAD/VAR-main/models/helpers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"arxiv_id":"2601.05246","paper":"/paper/arxiv-2601-05246","title":"Pixel-Perfect Visual Geometry Estimation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"gangweix/pixel-perfect-depth","path":"ppd/models/depth_anything_v2/dinov2_layers/drop_path.py","file_url":"https://github.com/gangweix/pixel-perfect-depth/blob/HEAD/ppd/models/depth_anything_v2/dinov2_layers/drop_path.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"arxiv_id":"2512.16202","paper":"/paper/arxiv-2512-16202","title":"Open Ad-hoc Categorization with Contextualized Feature Learning","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"Wayne2Wang/OAK","path":"src/models/dino_vision_transformer.py","file_url":"https://github.com/Wayne2Wang/OAK/blob/HEAD/src/models/dino_vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2511.16315","paper":"/paper/arxiv-2511-16315","title":"BioBench: A Blueprint to Move Beyond ImageNet for Scientific ML Benchmarks","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"samuelstevens/biobench","path":"src/biobench/webssl.py","file_url":"https://github.com/samuelstevens/biobench/blob/HEAD/src/biobench/webssl.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"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":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2507.11539","paper":"/paper/streaming-4d-visual-geometry-transformer","title":"Streaming 4D Visual Geometry Transformer","date":"2025-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wzzheng/streamvggt","path":"src/streamvggt/layers/drop_path.py","file_url":"https://github.com/wzzheng/streamvggt/blob/HEAD/src/streamvggt/layers/drop_path.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"arxiv_id":"2507.11415","paper":"/paper/u-rwkv-lightweight-medical-image-segmentation","title":"U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKV","date":"2025-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hbyecoding/u-rwkv","path":"models/cmunext/cmunext_rwkv_test_bk.py","file_url":"https://github.com/hbyecoding/u-rwkv/blob/HEAD/models/cmunext/cmunext_rwkv_test_bk.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"arxiv_id":"2507.03779","paper":null,"title":"arXiv:2507.03779","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"KevinZ0217/fast_dinov2","path":"dinov2/layers/drop_path.py","file_url":"https://github.com/KevinZ0217/fast_dinov2/blob/HEAD/dinov2/layers/drop_path.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"arxiv_id":"2506.22624","paper":"/paper/seg-r1-segmentation-can-be-surprisingly","title":"Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning","date":"2025-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"geshang777/FOCUS","path":"focus/modeling/edge_enhancer/edge_enhancer.py","file_url":"https://github.com/geshang777/FOCUS/blob/HEAD/focus/modeling/edge_enhancer/edge_enhancer.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":"4134f673786a2abe","mcp_get_code":{"code_sha256":"4134f673786a2abe"}},{"arxiv_id":"2506.13750","paper":"/paper/test3r-learning-to-reconstruct-3d-at-test","title":"Test3R: Learning to Reconstruct 3D at Test Time","date":"2025-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nopqaq/test3r","path":"croco/models/blocks.py","file_url":"https://github.com/nopqaq/test3r/blob/HEAD/croco/models/blocks.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f9a1900525331e0f","mcp_get_code":{"code_sha256":"f9a1900525331e0f"}},{"arxiv_id":"2505.19225","paper":"/paper/meditok-a-unified-tokenizer-for-medical-image","title":"MedITok: A Unified Tokenizer for Medical Image Synthesis and Interpretation","date":"2025-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"masaaki-75/meditok","path":"layers/drop_path.py","file_url":"https://github.com/masaaki-75/meditok/blob/HEAD/layers/drop_path.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"arxiv_id":"2505.12742","paper":"/paper/mvar-visual-autoregressive-modeling-with","title":"MVAR: Visual Autoregressive Modeling with Scale and Spatial Markovian Conditioning","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"labshuhanggu/mvar","path":"models/helpers.py","file_url":"https://github.com/labshuhanggu/mvar/blob/HEAD/models/helpers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"arxiv_id":"2505.12137","paper":"/paper/understanding-the-capabilities-of-molecular","title":"Understanding the Capabilities of Molecular Graph Neural Networks in Materials Science Through Multimodal Learning and Physical Context Encoding","date":"2025-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kurbanintelligencelab/understandingmultimodalgnns","path":"models/equiformer/drop.py","file_url":"https://github.com/kurbanintelligencelab/understandingmultimodalgnns/blob/HEAD/models/equiformer/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2505.04270","paper":"/paper/object-shot-enhanced-grounding-network-for","title":"Object-Shot Enhanced Grounding Network for Egocentric Video","date":"2025-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yisen-Feng/OSGNet","path":"libs/modeling/blocks.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/libs/modeling/blocks.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a34c005ba2203f35","mcp_get_code":{"code_sha256":"a34c005ba2203f35"}},{"arxiv_id":"2504.13181","paper":"/paper/perception-encoder-the-best-visual-embeddings","title":"Perception Encoder: The best visual embeddings are not at the output of the network","date":"2025-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/perception_models","path":"apps/detection/DETA_pe/models/swin.py","file_url":"https://github.com/facebookresearch/perception_models/blob/HEAD/apps/detection/DETA_pe/models/swin.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"arxiv_id":"2504.08222","paper":"/paper/f-3-set-towards-analyzing-fast-frequent-and","title":"F$^3$Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos","date":"2025-04-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"f3set/f3set","path":"model/impl/actionformer.py","file_url":"https://github.com/f3set/f3set/blob/HEAD/model/impl/actionformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a34c005ba2203f35","mcp_get_code":{"code_sha256":"a34c005ba2203f35"}},{"arxiv_id":"2504.03755","paper":"/paper/protogcd-unified-and-unbiased-prototype","title":"ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery","date":"2025-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mashijie1028/protogcd","path":"models/vision_transformer.py","file_url":"https://github.com/mashijie1028/protogcd/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2503.22405","paper":"/paper/modeling-multiple-normal-action","title":"Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks","date":"2025-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iSEE-Laboratory/AMNAR","path":"libs/modeling/blocks.py","file_url":"https://github.com/iSEE-Laboratory/AMNAR/blob/HEAD/libs/modeling/blocks.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a34c005ba2203f35","mcp_get_code":{"code_sha256":"a34c005ba2203f35"}},{"arxiv_id":"2503.11629","paper":"/paper/treemeshgpt-artistic-mesh-generation-with","title":"TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing","date":"2025-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/treemeshgpt","path":"model/pc_encoder.py","file_url":"https://github.com/sail-sg/treemeshgpt/blob/HEAD/model/pc_encoder.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"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":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"fe7d4321dbeef661","mcp_get_code":{"code_sha256":"fe7d4321dbeef661"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"10e67144852e5fce","mcp_get_code":{"code_sha256":"10e67144852e5fce"}},{"arxiv_id":"2503.08685","paper":"/paper/principal-components-enable-a-new-language-of","title":"\"Principal Components\" Enable A New Language of Images","date":"2025-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"visual-gen/semanticist","path":"semanticist/stage1/vision_transformer.py","file_url":"https://github.com/visual-gen/semanticist/blob/HEAD/semanticist/stage1/vision_transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4134f673786a2abe","mcp_get_code":{"code_sha256":"4134f673786a2abe"}},{"arxiv_id":"2503.08540","paper":"/paper/mellow-a-small-audio-language-model-for","title":"Mellow: a small audio language model for reasoning","date":"2025-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"soham97/mellow","path":"mellow/model/htsat.py","file_url":"https://github.com/soham97/mellow/blob/HEAD/mellow/model/htsat.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2502.20313","paper":"/paper/flexvar-flexible-visual-autoregressive","title":"FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction","date":"2025-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiaosiyu1999/FlexVAR","path":"models/helpers.py","file_url":"https://github.com/jiaosiyu1999/FlexVAR/blob/HEAD/models/helpers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"arxiv_id":"2502.17437","paper":"/paper/fractal-generative-models","title":"Fractal Generative Models","date":"2025-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LTH14/fractalgen","path":"models/ar.py","file_url":"https://github.com/LTH14/fractalgen/blob/HEAD/models/ar.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"arxiv_id":"2502.04476","paper":"/paper/adiff-explaining-audio-difference-using","title":"ADIFF: Explaining audio difference using natural language","date":"2025-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"soham97/adiff","path":"model/htsat.py","file_url":"https://github.com/soham97/adiff/blob/HEAD/model/htsat.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2501.18993","paper":"/paper/visual-autoregressive-modeling-for-image","title":"Visual Autoregressive Modeling for Image Super-Resolution","date":"2025-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qyp2000/varsr","path":"models/helpers.py","file_url":"https://github.com/qyp2000/varsr/blob/HEAD/models/helpers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"arxiv_id":"2501.18954","paper":"/paper/llmdet-learning-strong-open-vocabulary-object","title":"LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models","date":"2025-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iSEE-Laboratory/LLMDet","path":"hf_model/modeling_grounding_dino.py","file_url":"https://github.com/iSEE-Laboratory/LLMDet/blob/HEAD/hf_model/modeling_grounding_dino.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"b6822336792e87db","mcp_get_code":{"code_sha256":"b6822336792e87db"}},{"arxiv_id":"2501.12375","paper":"/paper/video-depth-anything-consistent-depth","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","date":"2025-01-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DepthAnything/Video-Depth-Anything","path":"video_depth_anything/dinov2_layers/drop_path.py","file_url":"https://github.com/DepthAnything/Video-Depth-Anything/blob/HEAD/video_depth_anything/dinov2_layers/drop_path.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"arxiv_id":"2412.16156","paper":"/paper/personalized-representation-from-personalized","title":"Personalized Representation from Personalized Generation","date":"2024-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ssundaram21/personalized-rep","path":"models/vision_transformer.py","file_url":"https://github.com/ssundaram21/personalized-rep/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2412.12628","paper":"/paper/dense-audio-visual-event-localization-under","title":"Dense Audio-Visual Event Localization under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration","date":"2024-12-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzhhfut/ccnet-aaai2025","path":"libs/modeling/blocks.py","file_url":"https://github.com/zzhhfut/ccnet-aaai2025/blob/HEAD/libs/modeling/blocks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"019e6b38831f1474","mcp_get_code":{"code_sha256":"019e6b38831f1474"}},{"arxiv_id":"2412.09401","paper":"/paper/slam3r-real-time-dense-scene-reconstruction","title":"SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pku-vcl-3dv/slam3r","path":"slam3r/blocks/basic_blocks.py","file_url":"https://github.com/pku-vcl-3dv/slam3r/blob/HEAD/slam3r/blocks/basic_blocks.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f9a1900525331e0f","mcp_get_code":{"code_sha256":"f9a1900525331e0f"}},{"arxiv_id":"2412.09032","paper":"/paper/speech-forensics-towards-comprehensive","title":"Speech-Forensics: Towards Comprehensive Synthetic Speech Dataset Establishment and Analysis","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ring-zl/Speech-Forensics","path":"libs/modeling/blocks.py","file_url":"https://github.com/ring-zl/Speech-Forensics/blob/HEAD/libs/modeling/blocks.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a34c005ba2203f35","mcp_get_code":{"code_sha256":"a34c005ba2203f35"}},{"arxiv_id":"2412.04431","paper":"/paper/infinity-scaling-bitwise-autoregressive","title":"Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis","date":"2024-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FoundationVision/VAR","path":"models/helpers.py","file_url":"https://github.com/FoundationVision/VAR/blob/HEAD/models/helpers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"arxiv_id":"2411.16289","paper":"/paper/utilizing-uncertainty-in-2d-pose-detectors","title":"Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery","date":"2024-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"twehrbein/humr","path":"easy_vitpose/vit.py","file_url":"https://github.com/twehrbein/humr/blob/HEAD/easy_vitpose/vit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"arxiv_id":"2411.15922","paper":"/paper/prompthsi-universal-hyperspectral-image","title":"PromptHSI: Universal Hyperspectral Image Restoration with Vision-Language Modulated Frequency Adaptation","date":"2024-11-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chingheng0808/PromptHSI","path":"utils/DRCT.py","file_url":"https://github.com/chingheng0808/PromptHSI/blob/HEAD/utils/DRCT.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"52d96aa31ed74a56","mcp_get_code":{"code_sha256":"52d96aa31ed74a56"}},{"arxiv_id":"2411.15867","paper":"/paper/panollama-generating-endless-and-coherent","title":"PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMs","date":"2024-11-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"0606zt/panollama","path":"utils/drop_path.py","file_url":"https://github.com/0606zt/panollama/blob/HEAD/utils/drop_path.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3aa4e8e74369506","mcp_get_code":{"code_sha256":"e3aa4e8e74369506"}},{"arxiv_id":"2411.15648","paper":"/paper/sample-and-parameter-efficient-auto","title":"Sample- and Parameter-Efficient Auto-Regressive Image Models","date":"2024-11-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"elad-amrani/xtra","path":"src/modules/vit.py","file_url":"https://github.com/elad-amrani/xtra/blob/HEAD/src/modules/vit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2411.15269","paper":"/paper/mambairv2-attentive-state-space-restoration","title":"MambaIRv2: Attentive State Space Restoration","date":"2024-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csguoh/mambair","path":"analysis/model_zoo/hat.py","file_url":"https://github.com/csguoh/mambair/blob/HEAD/analysis/model_zoo/hat.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"52d96aa31ed74a56","mcp_get_code":{"code_sha256":"52d96aa31ed74a56"}},{"arxiv_id":"2411.11471","paper":"/paper/generalizable-person-re-identification-via-2","title":"Generalizable Person Re-identification via Balancing Alignment and Uniformity","date":"2024-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yoonkicho/BAU","path":"bau/models/vit.py","file_url":"https://github.com/yoonkicho/BAU/blob/HEAD/bau/models/vit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"arxiv_id":"2411.11409","paper":"/paper/ikea-manuals-at-work-4d-grounding-of-assembly","title":"IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos","date":"2024-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yunongLiu1/IKEA-Manuals-at-Work","path":"src/IKEAVideo/featurizers/DINO.py","file_url":"https://github.com/yunongLiu1/IKEA-Manuals-at-Work/blob/HEAD/src/IKEAVideo/featurizers/DINO.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2411.11409","paper":"/paper/ikea-manuals-at-work-4d-grounding-of-assembly","title":"IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos","date":"2024-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yunongLiu1/IKEA-Manuals-at-Work","path":"src/IKEAVideo/featurizers/DINOv2.py","file_url":"https://github.com/yunongLiu1/IKEA-Manuals-at-Work/blob/HEAD/src/IKEAVideo/featurizers/DINOv2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8a105009df710b93","mcp_get_code":{"code_sha256":"8a105009df710b93"}},{"arxiv_id":"2411.10433","paper":"/paper/m-var-decoupled-scale-wise-autoregressive","title":"M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation","date":"2024-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oliverrensu/mvar","path":"models/helpers.py","file_url":"https://github.com/oliverrensu/mvar/blob/HEAD/models/helpers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"arxiv_id":"2411.02840","paper":"/paper/test-time-dynamic-image-fusion","title":"Test-Time Dynamic Image Fusion","date":"2024-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yinan-Xia/TTD","path":"net.py","file_url":"https://github.com/Yinan-Xia/TTD/blob/HEAD/net.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fe7d4321dbeef661","mcp_get_code":{"code_sha256":"fe7d4321dbeef661"}},{"arxiv_id":"2411.02327","paper":"/paper/ppllava-varied-video-sequence-understanding","title":"PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance","date":"2024-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"farewellthree/ppllava","path":"ppllava/models/clip_btadapter.py","file_url":"https://github.com/farewellthree/ppllava/blob/HEAD/ppllava/models/clip_btadapter.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":"9a83c0663b6afcd4","mcp_get_code":{"code_sha256":"9a83c0663b6afcd4"}},{"arxiv_id":"2411.01800","paper":"/paper/expanding-sparse-tuning-for-low-memory-usage","title":"Expanding Sparse Tuning for Low Memory Usage","date":"2024-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ssfgunner/SNELL","path":"model/utils.py","file_url":"https://github.com/ssfgunner/SNELL/blob/HEAD/model/utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"arxiv_id":"2410.21264","paper":"/paper/larp-tokenizing-videos-with-a-learned-1","title":"LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior","date":"2024-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hywang66/LARP","path":"models/larp_ar.py","file_url":"https://github.com/hywang66/LARP/blob/HEAD/models/larp_ar.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"arxiv_id":"2410.19553","paper":"/paper/on-occlusions-in-video-action-detection-1","title":"On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes","date":"2024-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rajatmodi62/OccludedActionBenchmark","path":"codebase/codebase_islands/slowfast/models/common.py","file_url":"https://github.com/rajatmodi62/OccludedActionBenchmark/blob/HEAD/codebase/codebase_islands/slowfast/models/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bcc1cdae3bb3212c","mcp_get_code":{"code_sha256":"bcc1cdae3bb3212c"}},{"arxiv_id":"2410.19213","paper":"/paper/prototypical-hash-encoding-for-on-the-fly","title":"Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery","date":"2024-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HaiyangZheng/PHE","path":"vision_transformer.py","file_url":"https://github.com/HaiyangZheng/PHE/blob/HEAD/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2410.12771","paper":"/paper/open-materials-2024-omat24-inorganic","title":"Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models","date":"2024-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"atomicarchitects/dens","path":"model/equiformer_v2/drop.py","file_url":"https://github.com/atomicarchitects/dens/blob/HEAD/model/equiformer_v2/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2410.10812","paper":"/paper/hart-efficient-visual-generation-with-hybrid","title":"HART: Efficient Visual Generation with Hybrid Autoregressive Transformer","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mit-han-lab/hart","path":"hart/modules/networks/utils.py","file_url":"https://github.com/mit-han-lab/hart/blob/HEAD/hart/modules/networks/utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"arxiv_id":"2410.10589","paper":"/paper/mote-reconciling-generalization-with","title":"MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZMHH-H/MoTE","path":"clip/model.py","file_url":"https://github.com/ZMHH-H/MoTE/blob/HEAD/clip/model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2410.06535","paper":"/paper/happy-a-debiased-learning-framework-for","title":"Happy: A Debiased Learning Framework for Continual Generalized Category Discovery","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mashijie1028/Happy-CGCD","path":"models/lora_vision_transformer.py","file_url":"https://github.com/mashijie1028/Happy-CGCD/blob/HEAD/models/lora_vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2409.13689","paper":"/paper/temporally-aligned-audio-for-video-with","title":"Temporally Aligned Audio for Video with Autoregression","date":"2024-09-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ilpoviertola/V-AURA","path":"utils/drop_path.py","file_url":"https://github.com/ilpoviertola/V-AURA/blob/HEAD/utils/drop_path.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"arxiv_id":"2409.13598","paper":"/paper/prithvi-wxc-foundation-model-for-weather-and","title":"Prithvi WxC: Foundation Model for Weather and Climate","date":"2024-09-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nasa-impact/prithvi-wxc","path":"PrithviWxC/model.py","file_url":"https://github.com/nasa-impact/prithvi-wxc/blob/HEAD/PrithviWxC/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9fb52d0e32d427ed","mcp_get_code":{"code_sha256":"9fb52d0e32d427ed"}},{"arxiv_id":"2409.10385","paper":"/paper/mamba-st-state-space-model-for-efficient","title":"Mamba-ST: State Space Model for Efficient Style Transfer","date":"2024-09-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"filippobotti/mambast","path":"models/ViT_helper.py","file_url":"https://github.com/filippobotti/mambast/blob/HEAD/models/ViT_helper.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2408.14371","paper":"/paper/selex-self-expertise-in-fine-grained","title":"SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery","date":"2024-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sarahrastegar/selex","path":"models/vision_transformer.py","file_url":"https://github.com/sarahrastegar/selex/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2408.13492","paper":"/paper/online-continuous-generalized-category","title":"Online Continuous Generalized Category Discovery","date":"2024-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"khu-agi/ocgcd","path":"net/vision_transformer.py","file_url":"https://github.com/khu-agi/ocgcd/blob/HEAD/net/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2408.10269","paper":"/paper/opencity-open-spatio-temporal-foundation","title":"OpenCity: Open Spatio-Temporal Foundation Models for Traffic Prediction","date":"2024-08-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hkuds/opencity","path":"model/OpenCity/OpenCity.py","file_url":"https://github.com/hkuds/opencity/blob/HEAD/model/OpenCity/OpenCity.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9bdf2492c6e0a8de","mcp_get_code":{"code_sha256":"9bdf2492c6e0a8de"}},{"arxiv_id":"2408.08447","paper":"/paper/spectralearth-training-hyperspectral","title":"SpectralEarth: Training Hyperspectral Foundation Models at Scale","date":"2024-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"panopticon-fm/panopticon","path":"dinov2/layers/drop_path.py","file_url":"https://github.com/panopticon-fm/panopticon/blob/HEAD/dinov2/layers/drop_path.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"arxiv_id":"2408.07919","paper":"/paper/advancing-multi-grained-alignment-for","title":"Advancing Multi-grained Alignment for Contrastive Language-Audio Pre-training","date":"2024-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ming-er/mga-clap","path":"models/htsat.py","file_url":"https://github.com/ming-er/mga-clap/blob/HEAD/models/htsat.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2408.01181","paper":"/paper/2408-01181","title":"VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling","date":"2024-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"daixiangzi/var-clip","path":"models/helpers.py","file_url":"https://github.com/daixiangzi/var-clip/blob/HEAD/models/helpers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"arxiv_id":"2407.19985","paper":"/paper/mixture-of-nested-experts-adaptive-processing","title":"Mixture of Nested Experts: Adaptive Processing of Visual Tokens","date":"2024-07-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"usryokousha/mone-pytorch","path":"mone_pytorch/layers/block.py","file_url":"https://github.com/usryokousha/mone-pytorch/blob/HEAD/mone_pytorch/layers/block.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"arxiv_id":"2407.17486","paper":"/paper/learning-from-memory-non-parametric-memory","title":"Learning from Memory: Non-Parametric Memory Augmented Self-Supervised Learning of Visual Features","date":"2024-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sthalles/MaSSL","path":"models/vision_transformer.py","file_url":"https://github.com/sthalles/MaSSL/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2407.14142","paper":"/paper/early-preparation-pays-off-new-classifier-pre","title":"Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation","date":"2024-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhengyuan-xie/ECCV24_NeST","path":"modules/backbone.py","file_url":"https://github.com/zhengyuan-xie/ECCV24_NeST/blob/HEAD/modules/backbone.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f5ab76486eeab7b9","mcp_get_code":{"code_sha256":"f5ab76486eeab7b9"}},{"arxiv_id":"2407.13483","paper":"/paper/scape-a-simple-and-strong-category-agnostic","title":"SCAPE: A Simple and Strong Category-Agnostic Pose Estimator","date":"2024-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tiny-smart/SCAPE","path":"scape/models/layers/drop_path.py","file_url":"https://github.com/tiny-smart/SCAPE/blob/HEAD/scape/models/layers/drop_path.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"arxiv_id":"2407.12622","paper":"/paper/rethinking-the-architecture-design-for","title":"Rethinking the Architecture Design for Efficient Generic Event Boundary Detection","date":"2024-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziwei-zheng/efficientgebd","path":"EffSoccerNet/diff_former.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/EffSoccerNet/diff_former.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"arxiv_id":"2407.10366","paper":"/paper/accessing-vision-foundation-models-at","title":"Accessing Vision Foundation Models at ImageNet-level Costs","date":"2024-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bespontaneous/proteus-pytorch","path":"pretrain/models_dinov2.py","file_url":"https://github.com/bespontaneous/proteus-pytorch/blob/HEAD/pretrain/models_dinov2.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"arxiv_id":"2407.09100","paper":"/paper/retrospective-for-the-dynamic-sensorium","title":"Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videos","date":"2024-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lRomul/sensorium","path":"src/models/dwiseneuro.py","file_url":"https://github.com/lRomul/sensorium/blob/HEAD/src/models/dwiseneuro.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"arxiv_id":"2407.08447","paper":"/paper/wildgaussians-3d-gaussian-splatting-in-the","title":"WildGaussians: 3D Gaussian Splatting in the Wild","date":"2024-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jkulhanek/wild-gaussians","path":"wildgaussians/dinov2.py","file_url":"https://github.com/jkulhanek/wild-gaussians/blob/HEAD/wildgaussians/dinov2.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"arxiv_id":"2407.06508","paper":"/paper/a-clinical-benchmark-of-public-self","title":"A Clinical Benchmark of Public Self-Supervised Pathology Foundation Models","date":"2024-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fuchs-lab-public/opal","path":"SSL_benchmarks/code/feature_extraction/vision_transformer.py","file_url":"https://github.com/fuchs-lab-public/opal/blob/HEAD/SSL_benchmarks/code/feature_extraction/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2407.05266","paper":"/paper/clamp-vit-contrastive-data-free-learning-for","title":"CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs","date":"2024-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"georgia-tech-synergy-lab/clamp-vit","path":"models/layers_quant.py","file_url":"https://github.com/georgia-tech-synergy-lab/clamp-vit/blob/HEAD/models/layers_quant.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2407.03197","paper":"/paper/dyfadet-dynamic-feature-aggregation-for","title":"DyFADet: Dynamic Feature Aggregation for Temporal Action Detection","date":"2024-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yangle15/DyFADet-pytorch","path":"libs/modeling/blocks.py","file_url":"https://github.com/yangle15/DyFADet-pytorch/blob/HEAD/libs/modeling/blocks.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a34c005ba2203f35","mcp_get_code":{"code_sha256":"a34c005ba2203f35"}},{"arxiv_id":"2407.02887","paper":"/paper/explicitly-guided-information-interaction","title":"Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion","date":"2024-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WHU-USI3DV/EGIInet","path":"models/layers/drop.py","file_url":"https://github.com/WHU-USI3DV/EGIInet/blob/HEAD/models/layers/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"314973a77b15948e","mcp_get_code":{"code_sha256":"314973a77b15948e"}},{"arxiv_id":"2406.15778","paper":"/paper/objectnlq-ego4d-episodic-memory-challenge","title":"ObjectNLQ @ Ego4D Episodic Memory Challenge 2024","date":"2024-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yisen-feng/objectnlq","path":"libs/modeling/blocks.py","file_url":"https://github.com/yisen-feng/objectnlq/blob/HEAD/libs/modeling/blocks.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a34c005ba2203f35","mcp_get_code":{"code_sha256":"a34c005ba2203f35"}},{"arxiv_id":"2406.14599","paper":"/paper/stylebreeder-exploring-and-democratizing","title":"Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models","date":"2024-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stylebreeder/stylebreeder-code","path":"models/dino_vits.py","file_url":"https://github.com/stylebreeder/stylebreeder-code/blob/HEAD/models/dino_vits.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2406.13392","paper":"/paper/strengthening-layer-interaction-via-dynamic","title":"Strengthening Layer Interaction via Dynamic Layer Attention","date":"2024-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tunantu/dynamic-layer-attention","path":"image_classification/cifar/models/cifar/dla_b.py","file_url":"https://github.com/tunantu/dynamic-layer-attention/blob/HEAD/image_classification/cifar/models/cifar/dla_b.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"arxiv_id":"2406.13275","paper":"/paper/enhancing-automated-audio-captioning-via","title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","date":"2024-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"frankenliu/LOAE","path":"models/ced/layers.py","file_url":"https://github.com/frankenliu/LOAE/blob/HEAD/models/ced/layers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"arxiv_id":"2406.09414","paper":"/paper/depth-anything-v2","title":"Depth Anything V2","date":"2024-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DepthAnything/Depth-Anything-V2","path":"depth_anything_v2/dinov2_layers/drop_path.py","file_url":"https://github.com/DepthAnything/Depth-Anything-V2/blob/HEAD/depth_anything_v2/dinov2_layers/drop_path.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"arxiv_id":"2406.09414","paper":"/paper/depth-anything-v2","title":"Depth Anything V2","date":"2024-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fabio-sim/Depth-Anything-ONNX","path":"depth_anything_v2/dinov2_layers/drop_path.py","file_url":"https://github.com/fabio-sim/Depth-Anything-ONNX/blob/HEAD/depth_anything_v2/dinov2_layers/drop_path.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":"7fd11117910b59f9","mcp_get_code":{"code_sha256":"7fd11117910b59f9"}},{"arxiv_id":"2406.07487","paper":"/paper/glad-towards-better-reconstruction-with","title":"GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hyao1/glad","path":"dino/vision_transformer.py","file_url":"https://github.com/hyao1/glad/blob/HEAD/dino/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2406.06973","paper":"/paper/rwkv-clip-a-robust-vision-language","title":"RWKV-CLIP: A Robust Vision-Language Representation Learner","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepglint/RWKV-CLIP","path":"model/utils_vision_rwkv/drop.py","file_url":"https://github.com/deepglint/RWKV-CLIP/blob/HEAD/model/utils_vision_rwkv/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"arxiv_id":"2406.05308","paper":"/paper/weakly-supervised-set-consistency-learning","title":"Weakly Supervised Set-Consistency Learning Improves Morphological Profiling of Single-Cell Images","date":"2024-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Genentech/set-dino","path":"vision_transformer.py","file_url":"https://github.com/Genentech/set-dino/blob/HEAD/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2405.21075","paper":"/paper/video-mme-the-first-ever-comprehensive","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PhysGame/PhysGame","path":"physvlm/models/clip_btadapter.py","file_url":"https://github.com/PhysGame/PhysGame/blob/HEAD/physvlm/models/clip_btadapter.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":"9a83c0663b6afcd4","mcp_get_code":{"code_sha256":"9a83c0663b6afcd4"}},{"arxiv_id":"2405.16567","paper":"/paper/automatic-jailbreaking-of-the-text-to-image","title":"Automatic Jailbreaking of the Text-to-Image Generative AI Systems","date":"2024-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Kim-Minseon/APGP","path":"vision_transformer.py","file_url":"https://github.com/Kim-Minseon/APGP/blob/HEAD/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2405.14700","paper":"/paper/sparse-tuning-adapting-vision-transformers","title":"Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuting20/sparse-tuning","path":"models/vit_image.py","file_url":"https://github.com/liuting20/sparse-tuning/blob/HEAD/models/vit_image.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"arxiv_id":"2405.14325","paper":"/paper/dinomaly-the-less-is-more-philosophy-in-multi","title":"Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guojiajeremy/dinomaly","path":"models/vision_transformer.py","file_url":"https://github.com/guojiajeremy/dinomaly/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2405.09873","paper":"/paper/irsrmamba-infrared-image-super-resolution-via","title":"IRSRMamba: Infrared Image Super-Resolution via Mamba-based Wavelet Transform Feature Modulation Model","date":"2024-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yongsongh/irsrmamba","path":"analysis/model_zoo/hat.py","file_url":"https://github.com/yongsongh/irsrmamba/blob/HEAD/analysis/model_zoo/hat.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"52d96aa31ed74a56","mcp_get_code":{"code_sha256":"52d96aa31ed74a56"}},{"arxiv_id":"2405.06283","paper":"/paper/novel-class-discovery-for-ultra-fine-grained","title":"Novel Class Discovery for Ultra-Fine-Grained Visual Categorization","date":"2024-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SSDUT-Caiyq/UFG-NCD","path":"models/vision_transformer.py","file_url":"https://github.com/SSDUT-Caiyq/UFG-NCD/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2405.04370","paper":"/paper/diff-ip2d-diffusion-based-hand-object","title":"Diff-IP2D: Diffusion-Based Hand-Object Interaction Prediction on Egocentric Videos","date":"2024-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"irmvlab/diff-ip2d","path":"diffip2d/transformer_model.py","file_url":"https://github.com/irmvlab/diff-ip2d/blob/HEAD/diffip2d/transformer_model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2404.15729","paper":"/paper/gradformer-graph-transformer-with-exponential","title":"Gradformer: Graph Transformer with Exponential Decay","date":"2024-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LiuChuang0059/Gradformer","path":"utils/droppath.py","file_url":"https://github.com/LiuChuang0059/Gradformer/blob/HEAD/utils/droppath.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"65b113a451720c90","mcp_get_code":{"code_sha256":"65b113a451720c90"}},{"arxiv_id":"2404.11273","paper":"/paper/training-transformer-models-by-wavelet-losses","title":"Training Transformer Models by Wavelet Losses Improves Quantitative and Visual Performance in Single Image Super-Resolution","date":"2024-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mandalinadagi/wavelettention","path":"wavelettention/archs/wavelettention_arch.py","file_url":"https://github.com/mandalinadagi/wavelettention/blob/HEAD/wavelettention/archs/wavelettention_arch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"52d96aa31ed74a56","mcp_get_code":{"code_sha256":"52d96aa31ed74a56"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"arxiv_id":"2404.07713","paper":"/paper/progressive-semantic-guided-vision","title":"Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning","date":"2024-04-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shiming-chen/zslvit","path":"zslvit.py","file_url":"https://github.com/shiming-chen/zslvit/blob/HEAD/zslvit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"arxiv_id":"2404.03392","paper":"/paper/two-tricks-to-improve-unsupervised","title":"Boosting Unsupervised Segmentation Learning","date":"2024-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alperensari/segmentation-tricks","path":"vision_transformer.py","file_url":"https://github.com/alperensari/segmentation-tricks/blob/HEAD/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2404.03179","paper":"/paper/uniav-unified-audio-visual-perception-for","title":"UniAV: Unified Audio-Visual Perception for Multi-Task Video Event Localization","date":"2024-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ttgeng233/UniAV","path":"libs/modeling/blocks.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/modeling/blocks.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a34c005ba2203f35","mcp_get_code":{"code_sha256":"a34c005ba2203f35"}},{"arxiv_id":"2404.02257","paper":"/paper/snag-scalable-and-accurate-video-grounding","title":"SnAG: Scalable and Accurate Video Grounding","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"happyharrycn/actionformer_release","path":"libs/modeling/blocks.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/modeling/blocks.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a34c005ba2203f35","mcp_get_code":{"code_sha256":"a34c005ba2203f35"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e37b79debce8d027","mcp_get_code":{"code_sha256":"e37b79debce8d027"}},{"arxiv_id":"2404.15506","paper":"/paper/metric3d-v2-a-versatile-monocular-geometric-1","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","date":"2024-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yvanyin/metric3d","path":"mono/model/backbones/ViT_DINO.py","file_url":"https://github.com/yvanyin/metric3d/blob/HEAD/mono/model/backbones/ViT_DINO.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"arxiv_id":"2404.00722","paper":"/paper/drct-saving-image-super-resolution-away-from","title":"DRCT: Saving Image Super-resolution away from Information Bottleneck","date":"2024-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"52d96aa31ed74a56","mcp_get_code":{"code_sha256":"52d96aa31ed74a56"}},{"arxiv_id":"2403.11708","paper":"/paper/implicit-discriminative-knowledge-learning","title":"Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification","date":"2024-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"1kk077/idkl","path":"IDKL/grad_cam/vit_model.py","file_url":"https://github.com/1kk077/idkl/blob/HEAD/IDKL/grad_cam/vit_model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fe7d4321dbeef661","mcp_get_code":{"code_sha256":"fe7d4321dbeef661"}},{"arxiv_id":"2403.11193","paper":"/paper/neural-markov-random-field-for-stereo","title":"Neural Markov Random Field for Stereo Matching","date":"2024-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aeolusguan/NMRF","path":"nmrf/models/NMP.py","file_url":"https://github.com/aeolusguan/NMRF/blob/HEAD/nmrf/models/NMP.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2721b1ad15d4ab2a","mcp_get_code":{"code_sha256":"2721b1ad15d4ab2a"}},{"arxiv_id":"2403.09192","paper":"/paper/pyra-parallel-yielding-re-activation-for","title":"PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation","date":"2024-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-mig/pyra","path":"model/utils.py","file_url":"https://github.com/thu-mig/pyra/blob/HEAD/model/utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"arxiv_id":"2403.07700","paper":"/paper/cuvler-enhanced-unsupervised-object","title":"CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformers","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shahaf-arica/CuVLER","path":"dino/vision_transformer.py","file_url":"https://github.com/shahaf-arica/CuVLER/blob/HEAD/dino/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2403.07591","paper":"/paper/robustifying-and-boosting-training-free","title":"Robustifying and Boosting Training-Free Neural Architecture Search","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hzf1174/RoBoT","path":"darts_space/utils.py","file_url":"https://github.com/hzf1174/RoBoT/blob/HEAD/darts_space/utils.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":"2c6bc306e5f9c38b","mcp_get_code":{"code_sha256":"2c6bc306e5f9c38b"}},{"arxiv_id":"2403.05856","paper":"/paper/pov-prompt-oriented-view-agnostic-learning","title":"POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-View World","date":"2024-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xuboshen/pov_acmmm2023","path":"slowfast/models/common.py","file_url":"https://github.com/xuboshen/pov_acmmm2023/blob/HEAD/slowfast/models/common.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":"bcc1cdae3bb3212c","mcp_get_code":{"code_sha256":"bcc1cdae3bb3212c"}},{"arxiv_id":"2403.01482","paper":"/paper/eagle-eigen-aggregation-learning-for-object","title":"EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation","date":"2024-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MICV-yonsei/EAGLE","path":"src_EAGLE/dino/vision_transformer.py","file_url":"https://github.com/MICV-yonsei/EAGLE/blob/HEAD/src_EAGLE/dino/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"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":"csguoh/MambaIR","path":"analysis/model_zoo/hat.py","file_url":"https://github.com/csguoh/MambaIR/blob/HEAD/analysis/model_zoo/hat.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"52d96aa31ed74a56","mcp_get_code":{"code_sha256":"52d96aa31ed74a56"}},{"arxiv_id":"2402.14789","paper":"/paper/self-guided-masked-autoencoders-for-domain","title":"Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"johnathan-xie/sma","path":"src/transformers/models/sma/modeling_sma.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/models/sma/modeling_sma.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e3aa4e8e74369506","mcp_get_code":{"code_sha256":"e3aa4e8e74369506"}},{"arxiv_id":"2402.11301","paper":"/paper/revit-enhancing-vision-transformers-with","title":"ReViT: Enhancing Vision Transformers Feature Diversity with Attention Residual Connections","date":"2024-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adiko1997/revit","path":"model/common.py","file_url":"https://github.com/adiko1997/revit/blob/HEAD/model/common.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"314973a77b15948e","mcp_get_code":{"code_sha256":"314973a77b15948e"}},{"arxiv_id":"2402.04841","paper":"/paper/data-efficient-large-vision-models-through","title":"Data-efficient Large Vision Models through Sequential Autoregression","date":"2024-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ggjy/delvm","path":"InternLM/internlm/model/modeling_vit.py","file_url":"https://github.com/ggjy/delvm/blob/HEAD/InternLM/internlm/model/modeling_vit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"arxiv_id":"2402.03138","paper":"/paper/just-cluster-it-an-approach-for-exploration","title":"Just Cluster It: An Approach for Exploration in High-Dimensions using Clustering and Pre-Trained Representations","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stefanwm13/just-cluster-it-public","path":"dinov2/layers/drop_path.py","file_url":"https://github.com/stefanwm13/just-cluster-it-public/blob/HEAD/dinov2/layers/drop_path.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"arxiv_id":"2402.01879","paper":"/paper/s-zero-gradient-based-optimization-of-ell-0","title":"$σ$-zero: Gradient-based Optimization of $\\ell_0$-norm Adversarial Examples","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cinofix/sigma-zero-adversarial-attack","path":"models/cifar10/c11_c12.py","file_url":"https://github.com/cinofix/sigma-zero-adversarial-attack/blob/HEAD/models/cifar10/c11_c12.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cc62fb1a937874d2","mcp_get_code":{"code_sha256":"cc62fb1a937874d2"}},{"arxiv_id":"2402.00282","paper":"/paper/pam-prompting-audio-language-models-for-audio","title":"PAM: Prompting Audio-Language Models for Audio Quality Assessment","date":"2024-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"soham97/pam","path":"PAM/models/htsat.py","file_url":"https://github.com/soham97/pam/blob/HEAD/PAM/models/htsat.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2401.11174","paper":"/paper/pixel-wise-recognition-for-holistic-surgical","title":"Pixel-Wise Recognition for Holistic Surgical Scene Understanding","date":"2024-01-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bcv-uniandes/grasp","path":"TAPIS/tapis/models/common.py","file_url":"https://github.com/bcv-uniandes/grasp/blob/HEAD/TAPIS/tapis/models/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bcc1cdae3bb3212c","mcp_get_code":{"code_sha256":"bcc1cdae3bb3212c"}},{"arxiv_id":"2401.10166","paper":"/paper/vmamba-visual-state-space-model","title":"VMamba: Visual State Space Model","date":"2024-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zs1314/microscopic-mamba","path":"grad_cam/vit_model.py","file_url":"https://github.com/zs1314/microscopic-mamba/blob/HEAD/grad_cam/vit_model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fe7d4321dbeef661","mcp_get_code":{"code_sha256":"fe7d4321dbeef661"}},{"arxiv_id":"2312.17243","paper":"/paper/unsupervised-universal-image-segmentation","title":"Unsupervised Universal Image Segmentation","date":"2023-12-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"u2seg/u2seg","path":"u2seg/Instance_Clustering/selective_labeling/dino.py","file_url":"https://github.com/u2seg/u2seg/blob/HEAD/u2seg/Instance_Clustering/selective_labeling/dino.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2312.16045","paper":"/paper/algebraic-positional-encodings","title":"Algebraic Positional Encodings","date":"2023-12-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"konstantinoskokos/unitarype","path":"ape/nn/drop_path.py","file_url":"https://github.com/konstantinoskokos/unitarype/blob/HEAD/ape/nn/drop_path.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"CC-BY-SA-4.0","inline_ok":false,"code_sha256_prefix":"e61c32bb0f3aa28d","mcp_get_code":{"code_sha256":"e61c32bb0f3aa28d"}},{"arxiv_id":"2312.12431","paper":"/paper/on-inference-stability-for-diffusion-models","title":"On Inference Stability for Diffusion Models","date":"2023-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vinairesearch/sa-dpm","path":"models/timm.py","file_url":"https://github.com/vinairesearch/sa-dpm/blob/HEAD/models/timm.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"arxiv_id":"2312.08010","paper":"/paper/ez-clip-efficient-zeroshot-video-action","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","date":"2023-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shahzadnit/ez-clip","path":"clip/model.py","file_url":"https://github.com/shahzadnit/ez-clip/blob/HEAD/clip/model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2312.07246","paper":"/paper/unifying-correspondence-pose-and-nerf-for","title":"Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs","date":"2023-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KU-CVLAB/CoPoNeRF","path":"models/backbone.py","file_url":"https://github.com/KU-CVLAB/CoPoNeRF/blob/HEAD/models/backbone.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e60d6e23233f6f4b","mcp_get_code":{"code_sha256":"e60d6e23233f6f4b"}},{"arxiv_id":"2312.03703","paper":"/paper/skeleton-in-context-unified-skeleton-sequence","title":"Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning","date":"2023-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fanglaosi/skeleton-in-context","path":"lib/model/drop.py","file_url":"https://github.com/fanglaosi/skeleton-in-context/blob/HEAD/lib/model/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2312.02366","paper":"/paper/towards-general-purpose-vision-foundation","title":"Evaluating General Purpose Vision Foundation Models for Medical Image Analysis: An Experimental Study of DINOv2 on Radiology Benchmarks","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mohammedsb/dinov2formedical","path":"dinov2/layers/drop_path.py","file_url":"https://github.com/mohammedsb/dinov2formedical/blob/HEAD/dinov2/layers/drop_path.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"arxiv_id":"2312.01623","paper":"/paper/universal-segmentation-at-arbitrary","title":"Universal Segmentation at Arbitrary Granularity with Language Instruction","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"workforai/UniLSeg","path":"model/swin_basic.py","file_url":"https://github.com/workforai/UniLSeg/blob/HEAD/model/swin_basic.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2311.18649","paper":"/paper/simple-semantic-aided-few-shot-learning","title":"Simple Semantic-Aided Few-Shot Learning","date":"2023-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhangdoudou123/semfew","path":"model/vision_transformer.py","file_url":"https://github.com/zhangdoudou123/semfew/blob/HEAD/model/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2311.17893","paper":"/paper/betrayed-by-attention-a-simple-yet-effective","title":"Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation","date":"2023-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shvdiwnkozbw/ssl-uvos","path":"src/model/vision_transformer.py","file_url":"https://github.com/shvdiwnkozbw/ssl-uvos/blob/HEAD/src/model/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2311.16917","paper":"/paper/ugg-unified-generative-grasping","title":"UGG: Unified Generative Grasping","date":"2023-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jiaxin-Lu/ugg","path":"model/ugg/UViT/timm.py","file_url":"https://github.com/Jiaxin-Lu/ugg/blob/HEAD/model/ugg/UViT/timm.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"arxiv_id":"2311.16432","paper":"/paper/text-driven-image-editing-via-learnable","title":"Text-Driven Image Editing via Learnable Regions","date":"2023-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuanze-lin/Learnable_Regions","path":"models/vision_transformer.py","file_url":"https://github.com/yuanze-lin/Learnable_Regions/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2311.11600","paper":"/paper/deep-equilibrium-diffusion-restoration-with","title":"Deep Equilibrium Diffusion Restoration with Parallel Sampling","date":"2023-11-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"caojiezhang/deqir","path":"models/hat_arch.py","file_url":"https://github.com/caojiezhang/deqir/blob/HEAD/models/hat_arch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"52d96aa31ed74a56","mcp_get_code":{"code_sha256":"52d96aa31ed74a56"}},{"arxiv_id":"2311.09084","paper":"/paper/contrastive-transformer-learning-with","title":"Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hcplab-sysu/personsearch-ctlg","path":"models/vit.py","file_url":"https://github.com/hcplab-sysu/personsearch-ctlg/blob/HEAD/models/vit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"arxiv_id":"2311.05152","paper":"/paper/cross-modal-prompts-adapting-large-pre","title":"Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks","date":"2023-11-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoyi-duan/DG-SCT","path":"DG-SCT/AVE/nets/layers.py","file_url":"https://github.com/haoyi-duan/DG-SCT/blob/HEAD/DG-SCT/AVE/nets/layers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2311.04442","paper":"/paper/ss-mae-spatial-spectral-masked-auto-encoder","title":"SS-MAE: Spatial-Spectral Masked Auto-Encoder for Multi-Source Remote Sensing Image Classification","date":"2023-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"summitgao/ss-mae","path":"net/VIT/layers/drop.py","file_url":"https://github.com/summitgao/ss-mae/blob/HEAD/net/VIT/layers/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"arxiv_id":"2311.02326","paper":"/paper/fragxsitedti-revealing-responsible-segments","title":"FragXsiteDTI: Revealing Responsible Segments in Drug-Target Interaction with Transformer-Driven Interpretation","date":"2023-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yazdanimehdi/fragxsitedti","path":"layers.py","file_url":"https://github.com/yazdanimehdi/fragxsitedti/blob/HEAD/layers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"arxiv_id":"2311.00180","paper":"/paper/object-centric-video-representation-for-long","title":"Object-centric Video Representation for Long-term Action Anticipation","date":"2023-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brown-palm/ObjectPrompt","path":"src/models/mvit.py","file_url":"https://github.com/brown-palm/ObjectPrompt/blob/HEAD/src/models/mvit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bcc1cdae3bb3212c","mcp_get_code":{"code_sha256":"bcc1cdae3bb3212c"}},{"arxiv_id":"2310.19776","paper":"/paper/learn-to-categorize-or-categorize-to-learn-1","title":"Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery","date":"2023-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SarahRastegar/InfoSieve","path":"models/vision_transformer.py","file_url":"https://github.com/SarahRastegar/InfoSieve/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2310.17874","paper":"/paper/smooseg-smoothness-prior-for-unsupervised-1","title":"SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation","date":"2023-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mc-lan/smooseg","path":"models/dino/vision_transformer.py","file_url":"https://github.com/mc-lan/smooseg/blob/HEAD/models/dino/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2310.11881","paper":"/paper/a-comparative-study-of-image-restoration","title":"A Comparative Study of Image Restoration Networks for General Backbone Network Design","date":"2023-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andrew0613/x-restormer","path":"xrestormer/archs/Uformer_arch.py","file_url":"https://github.com/andrew0613/x-restormer/blob/HEAD/xrestormer/archs/Uformer_arch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"52d96aa31ed74a56","mcp_get_code":{"code_sha256":"52d96aa31ed74a56"}},{"arxiv_id":"2310.10207","paper":"/paper/bongard-openworld-few-shot-reasoning-for-free","title":"Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joyjayng/Bongard-OpenWorld","path":"models/encoder/swin_transformer.py","file_url":"https://github.com/joyjayng/Bongard-OpenWorld/blob/HEAD/models/encoder/swin_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2310.07855","paper":"/paper/cribo-self-supervised-learning-via-cross","title":"CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tileb1/CrIBo","path":"segmentation/models/dino_vision_transformer.py","file_url":"https://github.com/tileb1/CrIBo/blob/HEAD/segmentation/models/dino_vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2310.05184","paper":"/paper/aanet-aggregation-and-alignment-network-with","title":"AANet: Aggregation and Alignment Network with Semi-hard Positive Sample Mining for Hierarchical Place Recognition","date":"2023-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Lu-Feng/AANet","path":"model/cct/stochastic_depth.py","file_url":"https://github.com/Lu-Feng/AANet/blob/HEAD/model/cct/stochastic_depth.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6bb7492655ecbda4","mcp_get_code":{"code_sha256":"6bb7492655ecbda4"}},{"arxiv_id":"2310.00377","paper":null,"title":"arXiv:2310.00377","date":null,"month_inferred_from_arxiv_id":"2023-10","title_source":null,"repo":"GauravBh1010tt/DPViT","path":"models/vision_transformer.py","file_url":"https://github.com/GauravBh1010tt/DPViT/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2309.17342","paper":"/paper/towards-free-data-selection-with-general-1","title":"Towards Free Data Selection with General-Purpose Models","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yichen928/FreeSel","path":"data_selection/vision_transformer.py","file_url":"https://github.com/yichen928/FreeSel/blob/HEAD/data_selection/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2309.16217","paper":"/paper/gaflow-incorporating-gaussian-attention-into-1","title":"GAFlow: Incorporating Gaussian Attention into Optical Flow","date":"2023-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LA30/GAFlow","path":"core/model/encoder_gmflownet.py","file_url":"https://github.com/LA30/GAFlow/blob/HEAD/core/model/encoder_gmflownet.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"arxiv_id":"2309.16108","paper":"/paper/channel-vision-transformers-an-image-is-worth","title":"Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words","date":"2023-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"insitro/channelvit","path":"channelvit/backbone/vit.py","file_url":"https://github.com/insitro/channelvit/blob/HEAD/channelvit/backbone/vit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2309.08153","paper":"/paper/fine-tune-the-pretrained-atst-model-for-sound","title":"Fine-tune the pretrained ATST model for sound event detection","date":"2023-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Audio-WestlakeU/ATST-SED","path":"desed_task/nnet/atst/transformer.py","file_url":"https://github.com/Audio-WestlakeU/ATST-SED/blob/HEAD/desed_task/nnet/atst/transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2309.07911","paper":"/paper/disentangling-spatial-and-temporal-learning","title":"Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning","date":"2023-09-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba-mmai-research/dist","path":"models/base/base_blocks.py","file_url":"https://github.com/alibaba-mmai-research/dist/blob/HEAD/models/base/base_blocks.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f450abfe243be2a1","mcp_get_code":{"code_sha256":"f450abfe243be2a1"}},{"arxiv_id":"2309.05767","paper":"/paper/natural-language-supervision-for-general","title":"Natural Language Supervision for General-Purpose Audio Representations","date":null,"month_inferred_from_arxiv_id":"2023-09","title_source":"archive","repo":"microsoft/clap","path":"msclap/models/htsat.py","file_url":"https://github.com/microsoft/clap/blob/HEAD/msclap/models/htsat.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2309.05300","paper":"/paper/decur-decoupling-common-unique","title":"Decoupling Common and Unique Representations for Multimodal Self-supervised Learning","date":"2023-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhu-xlab/dino-mm","path":"models/dino/vision_transformer.py","file_url":"https://github.com/zhu-xlab/dino-mm/blob/HEAD/models/dino/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2309.05239","paper":"/paper/hat-hybrid-attention-transformer-for-image","title":"HAT: Hybrid Attention Transformer for Image Restoration","date":"2023-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chxy95/hat","path":"hat/archs/hat_arch.py","file_url":"https://github.com/chxy95/hat/blob/HEAD/hat/archs/hat_arch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"52d96aa31ed74a56","mcp_get_code":{"code_sha256":"52d96aa31ed74a56"}},{"arxiv_id":"2309.04195","paper":"/paper/towards-mitigating-architecture-overfitting","title":"Towards Mitigating Architecture Overfitting on Distilled Datasets","date":"2023-09-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cityu-mlo/mitigate_architecture_overfitting","path":"model.py","file_url":"https://github.com/cityu-mlo/mitigate_architecture_overfitting/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cc62fb1a937874d2","mcp_get_code":{"code_sha256":"cc62fb1a937874d2"}},{"arxiv_id":"2308.13772","paper":"/paper/boosting-residual-networks-with-group","title":"Boosting Residual Networks with Group Knowledge","date":"2023-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tsj-001/aaai24-gkt","path":"gkt/model_bank/cait_ddp.py","file_url":"https://github.com/tsj-001/aaai24-gkt/blob/HEAD/gkt/model_bank/cait_ddp.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f3c67c589b630c22","mcp_get_code":{"code_sha256":"f3c67c589b630c22"}},{"arxiv_id":"2308.12112","paper":"/paper/generalized-continual-category-discovery","title":"Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery","date":"2023-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"grypesc/camp","path":"approaches/networks/vit.py","file_url":"https://github.com/grypesc/camp/blob/HEAD/approaches/networks/vit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2308.11957","paper":"/paper/ced-consistent-ensemble-distillation-for","title":"CED: Consistent ensemble distillation for audio tagging","date":null,"month_inferred_from_arxiv_id":"2023-08","title_source":"archive","repo":"richermans/ced","path":"models/layers.py","file_url":"https://github.com/richermans/ced/blob/HEAD/models/layers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"arxiv_id":"2308.11796","paper":"/paper/time-does-tell-self-supervised-time-tuning-of","title":"Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations","date":"2023-08-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"smsd75/timetuning","path":"dino_vision_transformer.py","file_url":"https://github.com/smsd75/timetuning/blob/HEAD/dino_vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2308.11063","paper":"/paper/metagcd-learning-to-continually-learn-in","title":"MetaGCD: Learning to Continually Learn in Generalized Category Discovery","date":"2023-08-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ynanwu/metagcd","path":"models/vision_transformer.py","file_url":"https://github.com/ynanwu/metagcd/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2308.07092","paper":"/paper/masked-motion-predictors-are-strong-3d-action","title":"Masked Motion Predictors are Strong 3D Action Representation Learners","date":"2023-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maoyunyao/mamp","path":"model_mamp/drop.py","file_url":"https://github.com/maoyunyao/mamp/blob/HEAD/model_mamp/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2308.04808","paper":"/paper/joint-relation-transformer-for-multi-person","title":"Joint-Relation Transformer for Multi-Person Motion Prediction","date":"2023-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mediabrain-sjtu/jrtransformer","path":"model/model.py","file_url":"https://github.com/mediabrain-sjtu/jrtransformer/blob/HEAD/model/model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"arxiv_id":"2308.01948","paper":"/paper/a-multidimensional-analysis-of-social-biases","title":"A Multidimensional Analysis of Social Biases in Vision Transformers","date":"2023-08-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jannik-brinkmann/social-biases-in-vision-transformers","path":"src/embedding_extractors/models/dino/vision_transformer.py","file_url":"https://github.com/jannik-brinkmann/social-biases-in-vision-transformers/blob/HEAD/src/embedding_extractors/models/dino/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2307.16715","paper":"/paper/univtg-towards-unified-video-language","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","date":"2023-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"showlab/univtg","path":"model/transformer_encoder_droppath.py","file_url":"https://github.com/showlab/univtg/blob/HEAD/model/transformer_encoder_droppath.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"10e67144852e5fce","mcp_get_code":{"code_sha256":"10e67144852e5fce"}},{"arxiv_id":"2307.16508","paper":"/paper/towards-general-low-light-raw-noise-synthesis","title":"Towards General Low-Light Raw Noise Synthesis and Modeling","date":"2023-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fengzhang427/LRD","path":"ViT_helper.py","file_url":"https://github.com/fengzhang427/LRD/blob/HEAD/ViT_helper.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2307.16425","paper":"/paper/all-in-one-metrical-and-functional-structure","title":"All-In-One Metrical And Functional Structure Analysis With Neighborhood Attentions on Demixed Audio","date":"2023-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mir-aidj/all-in-one","path":"src/allin1/models/dinat.py","file_url":"https://github.com/mir-aidj/all-in-one/blob/HEAD/src/allin1/models/dinat.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"27dbb535e26ff63b","mcp_get_code":{"code_sha256":"27dbb535e26ff63b"}},{"arxiv_id":"2307.16184","paper":"/paper/unified-model-for-image-video-audio-and","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","date":"2023-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mshukor/unival","path":"models/unival/resnet.py","file_url":"https://github.com/mshukor/unival/blob/HEAD/models/unival/resnet.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":"52471eacb56db726","mcp_get_code":{"code_sha256":"52471eacb56db726"}},{"arxiv_id":"2307.16184","paper":"/paper/unified-model-for-image-video-audio-and","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","date":"2023-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mshukor/unival","path":"models/unival/unify_transformer_layer.py","file_url":"https://github.com/mshukor/unival/blob/HEAD/models/unival/unify_transformer_layer.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":"90fa02b8cae75fe7","mcp_get_code":{"code_sha256":"90fa02b8cae75fe7"}},{"arxiv_id":"2307.10802","paper":"/paper/meta-transformer-a-unified-framework-for","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","date":"2023-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"invictus717/MetaTransformer","path":"Graph/metatransformer/modules/droppath.py","file_url":"https://github.com/invictus717/MetaTransformer/blob/HEAD/Graph/metatransformer/modules/droppath.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":"49eae9f4f9e2a885","mcp_get_code":{"code_sha256":"49eae9f4f9e2a885"}},{"arxiv_id":"2307.06099","paper":"/paper/rfenet-towards-reciprocal-feature-evolution","title":"RFENet: Towards Reciprocal Feature Evolution for Glass Segmentation","date":"2023-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vankouf/rfenet","path":"network/mutual_process/drop.py","file_url":"https://github.com/vankouf/rfenet/blob/HEAD/network/mutual_process/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2306.16545","paper":"/paper/palm-predicting-actions-through-language","title":"Palm: Predicting Actions through Language Models @ Ego4D Long-Term Action Anticipation Challenge 2023","date":"2023-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dandoge/palm","path":"ego4d_forecasting/models/video_model_builder.py","file_url":"https://github.com/dandoge/palm/blob/HEAD/ego4d_forecasting/models/video_model_builder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bcc1cdae3bb3212c","mcp_get_code":{"code_sha256":"bcc1cdae3bb3212c"}},{"arxiv_id":"2306.12059","paper":"/paper/equiformerv2-improved-equivariant-transformer","title":"EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations","date":"2023-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"atomicarchitects/equiformer_v2","path":"nets/equiformer_v2/drop.py","file_url":"https://github.com/atomicarchitects/equiformer_v2/blob/HEAD/nets/equiformer_v2/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2306.07050","paper":"/paper/revisiting-token-pruning-for-object-detection","title":"Revisiting Token Pruning for Object Detection and Instance Segmentation","date":"2023-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uzh-rpg/svit","path":"classification/TransformerEncoderLayer.py","file_url":"https://github.com/uzh-rpg/svit/blob/HEAD/classification/TransformerEncoderLayer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}},{"arxiv_id":"2306.05031","paper":"/paper/generalizable-lightweight-proxy-for-robust-1","title":"Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations","date":"2023-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hyeonjeongha/croze","path":"zero_cost_methods/pruners/measures/croze.py","file_url":"https://github.com/hyeonjeongha/croze/blob/HEAD/zero_cost_methods/pruners/measures/croze.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"13c2719404e25b25","mcp_get_code":{"code_sha256":"13c2719404e25b25"}},{"arxiv_id":"2306.04362","paper":"/paper/youku-mplug-a-10-million-large-scale-chinese","title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks","date":"2023-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"x-plug/youku-mplug","path":"models/clip_video.py","file_url":"https://github.com/x-plug/youku-mplug/blob/HEAD/models/clip_video.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2306.03403","paper":"/paper/sgat4pass-spherical-geometry-aware","title":"SGAT4PASS: Spherical Geometry-Aware Transformer for PAnoramic Semantic Segmentation","date":"2023-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TencentARC/SGAT4PASS","path":"segmentron/modules/drop.py","file_url":"https://github.com/TencentARC/SGAT4PASS/blob/HEAD/segmentron/modules/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2306.02115","paper":"/paper/table-and-image-generation-for-investigating","title":"Table and Image Generation for Investigating Knowledge of Entities in Pre-trained Vision and Language Models","date":"2023-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OFA-Sys/OFA","path":"models/ofa/resnet.py","file_url":"https://github.com/OFA-Sys/OFA/blob/HEAD/models/ofa/resnet.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":"52471eacb56db726","mcp_get_code":{"code_sha256":"52471eacb56db726"}},{"arxiv_id":"2305.18500","paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TXH-mercury/VALOR","path":"model/videoswin.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/videoswin.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2305.13311","paper":"/paper/vdt-an-empirical-study-on-video-diffusion","title":"VDT: General-purpose Video Diffusion Transformers via Mask Modeling","date":"2023-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2305.11834","paper":"/paper/pengi-an-audio-language-model-for-audio-tasks-1","title":"Pengi: An Audio Language Model for Audio Tasks","date":"2023-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/pengi","path":"models/htsat.py","file_url":"https://github.com/microsoft/pengi/blob/HEAD/models/htsat.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2305.11435","paper":"/paper/syllable-discovery-and-cross-lingual","title":"Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model","date":"2023-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jasonppy/syllable-discovery","path":"models/vision_transformer.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2305.07304","paper":"/paper/clip-count-towards-text-guided-zero-shot","title":"CLIP-Count: Towards Text-Guided Zero-Shot Object Counting","date":"2023-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"songrise/clip-count","path":"models/models_crossvit.py","file_url":"https://github.com/songrise/clip-count/blob/HEAD/models/models_crossvit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e3aa4e8e74369506","mcp_get_code":{"code_sha256":"e3aa4e8e74369506"}},{"arxiv_id":"2305.06144","paper":"/paper/learning-semi-supervised-gaussian-mixture","title":"Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery","date":"2023-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DTennant/GPC","path":"models/vision_transformer.py","file_url":"https://github.com/DTennant/GPC/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2305.05140","paper":"/paper/linguistic-more-taking-a-further-step-toward","title":"Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition","date":"2023-05-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CyrilSterling/LPV","path":"modules/svtr_backbone.py","file_url":"https://github.com/CyrilSterling/LPV/blob/HEAD/modules/svtr_backbone.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ee6f01cbc95c7313","mcp_get_code":{"code_sha256":"ee6f01cbc95c7313"}},{"arxiv_id":"2305.00163","paper":"/paper/an-implicit-alignment-for-video-super","title":"Enhancing Video Super-Resolution via Implicit Resampling-based Alignment","date":"2023-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kai422/iart","path":"archs/psrt_sliding_arch.py","file_url":"https://github.com/kai422/iart/blob/HEAD/archs/psrt_sliding_arch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"52d96aa31ed74a56","mcp_get_code":{"code_sha256":"52d96aa31ed74a56"}},{"arxiv_id":"2304.14919","paper":"/paper/scatterformer-locally-invariant-scattering","title":"ScatterFormer: Locally-Invariant Scattering Transformer for Patient-Independent Multispectral Detection of Epileptiform Discharges","date":"2023-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"albertcheng19/scatterformer","path":"fourier_former.py","file_url":"https://github.com/albertcheng19/scatterformer/blob/HEAD/fourier_former.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"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":"beneroth13/dinov2","path":"dinov2/layers/drop_path.py","file_url":"https://github.com/beneroth13/dinov2/blob/HEAD/dinov2/layers/drop_path.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f5ab76486eeab7b9","mcp_get_code":{"code_sha256":"f5ab76486eeab7b9"}},{"arxiv_id":"2303.17176","paper":"/paper/a-view-from-somewhere-human-centric-face","title":"A View From Somewhere: Human-Centric Face Representations","date":"2023-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yukimasano/PASS","path":"vision_transformer.py","file_url":"https://github.com/yukimasano/PASS/blob/HEAD/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2303.16947","paper":"/paper/de-coupling-and-de-positioning-dense-self","title":"De-coupling and De-positioning Dense Self-supervised Learning","date":"2023-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ztt1024/densessl","path":"models/vision_transformer.py","file_url":"https://github.com/ztt1024/densessl/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2303.15111","paper":"/paper/learning-attention-as-disentangler-for","title":"Learning Attention as Disentangler for Compositional Zero-shot Learning","date":"2023-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoosz/ade-czsl","path":"models/multi_head_attention.py","file_url":"https://github.com/haoosz/ade-czsl/blob/HEAD/models/multi_head_attention.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2303.13245","paper":"/paper/croc-cross-view-online-clustering-for-dense","title":"CrOC: Cross-View Online Clustering for Dense Visual Representation Learning","date":"2023-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stegmuel/CrOC","path":"models/vision_transformer.py","file_url":"https://github.com/stegmuel/CrOC/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2303.12930","paper":"/paper/dense-localizing-audio-visual-events-in","title":"Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline","date":"2023-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ttgeng233/UnAV","path":"libs/modeling/blocks.py","file_url":"https://github.com/ttgeng233/UnAV/blob/HEAD/libs/modeling/blocks.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a34c005ba2203f35","mcp_get_code":{"code_sha256":"a34c005ba2203f35"}},{"arxiv_id":"2303.11906","paper":"/paper/solving-oscillation-problem-in-post-training","title":"Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective","date":"2023-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/mrecg","path":"models/layer/drop_path.py","file_url":"https://github.com/bytedance/mrecg/blob/HEAD/models/layer/drop_path.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2303.09447","paper":"/paper/steering-prototype-with-prompt-tuning-for","title":"Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning","date":"2023-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lzvv123456/contrastive-prototypical-prompt","path":"transformers/dino_vit.py","file_url":"https://github.com/lzvv123456/contrastive-prototypical-prompt/blob/HEAD/transformers/dino_vit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2303.09165","paper":"/paper/a-new-benchmark-on-the-utility-of-synthetic","title":"A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation","date":"2023-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huitangtang/on_the_utility_of_synthetic_data","path":"supervised_learning/models/vision_transformer.py","file_url":"https://github.com/huitangtang/on_the_utility_of_synthetic_data/blob/HEAD/supervised_learning/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2303.07347","paper":"/paper/tridet-temporal-action-detection-with","title":"TriDet: Temporal Action Detection with Relative Boundary Modeling","date":"2023-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dingfengshi/TriDet","path":"libs/modeling/blocks.py","file_url":"https://github.com/dingfengshi/TriDet/blob/HEAD/libs/modeling/blocks.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a34c005ba2203f35","mcp_get_code":{"code_sha256":"a34c005ba2203f35"}},{"arxiv_id":"2303.06440","paper":"/paper/xformer-hybrid-x-shaped-transformer-for-image","title":"Xformer: Hybrid X-Shaped Transformer for Image Denoising","date":"2023-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gladzhang/Xformer","path":"basicsr/models/archs/Xformer_arch.py","file_url":"https://github.com/gladzhang/Xformer/blob/HEAD/basicsr/models/archs/Xformer_arch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3aa4e8e74369506","mcp_get_code":{"code_sha256":"e3aa4e8e74369506"}},{"arxiv_id":"2303.02982","paper":"/paper/clip-guided-prototype-modulating-for-few-shot","title":"CLIP-guided Prototype Modulating for Few-shot Action Recognition","date":"2023-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba-mmai-research/clip-fsar","path":"models/base/base_blocks.py","file_url":"https://github.com/alibaba-mmai-research/clip-fsar/blob/HEAD/models/base/base_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":"f450abfe243be2a1","mcp_get_code":{"code_sha256":"f450abfe243be2a1"}},{"arxiv_id":"2302.10586","paper":"/paper/diffusion-models-and-semi-supervised-learners-1","title":"Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels","date":"2023-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ML-GSAI/DPT","path":"src/deit.py","file_url":"https://github.com/ML-GSAI/DPT/blob/HEAD/src/deit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2302.07387","paper":"/paper/polyformer-referring-image-segmentation-as","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","date":"2023-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/polygon-transformer","path":"models/polyformer/unify_transformer_layer.py","file_url":"https://github.com/amazon-science/polygon-transformer/blob/HEAD/models/polyformer/unify_transformer_layer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"90fa02b8cae75fe7","mcp_get_code":{"code_sha256":"90fa02b8cae75fe7"}},{"arxiv_id":"2302.04869","paper":"/paper/reversible-vision-transformers-1","title":"Reversible Vision Transformers","date":"2023-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/SlowFast","path":"slowfast/models/common.py","file_url":"https://github.com/facebookresearch/SlowFast/blob/HEAD/slowfast/models/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"bcc1cdae3bb3212c","mcp_get_code":{"code_sha256":"bcc1cdae3bb3212c"}},{"arxiv_id":"2302.03453","paper":"/paper/osrt-omnidirectional-image-super-resolution","title":"OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer","date":"2023-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fanghua-yu/osrt","path":"odisr/archs/osrt_arch.py","file_url":"https://github.com/fanghua-yu/osrt/blob/HEAD/odisr/archs/osrt_arch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9ea4d5b8b4d5ef2f","mcp_get_code":{"code_sha256":"9ea4d5b8b4d5ef2f"}},{"arxiv_id":"2302.00402","paper":"/paper/mplug-2-a-modularized-multi-modal-foundation","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","date":"2023-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"X-PLUG/mPLUG-2","path":"models/clip_video.py","file_url":"https://github.com/X-PLUG/mPLUG-2/blob/HEAD/models/clip_video.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2301.13156","paper":"/paper/seaformer-squeeze-enhanced-axial-transformer","title":"SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition","date":"2023-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fudan-zvg/SeaFormer","path":"seaformer-cls/seaformer.py","file_url":"https://github.com/fudan-zvg/SeaFormer/blob/HEAD/seaformer-cls/seaformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2301.12246","paper":"/paper/a-closer-look-at-few-shot-classification","title":"A Closer Look at Few-shot Classification Again","date":"2023-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2301.00184","paper":"/paper/cap4video-what-can-auxiliary-captions-do-for","title":"Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?","date":"2022-12-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"whwu95/BIKE","path":"clip/model.py","file_url":"https://github.com/whwu95/BIKE/blob/HEAD/clip/model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2212.05853","paper":"/paper/deepcut-unsupervised-segmentation-using-graph","title":"DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering","date":"2022-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sampl-weizmann/deepcut","path":"vision_transformer.py","file_url":"https://github.com/sampl-weizmann/deepcut/blob/HEAD/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2212.05590","paper":"/paper/promptcal-contrastive-affinity-learning-via","title":"PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery","date":"2022-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sheng-eatamath/promptcal","path":"models/vision_transformer.py","file_url":"https://github.com/sheng-eatamath/promptcal/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2211.14461","paper":"/paper/cddfuse-correlation-driven-dual-branch","title":"CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion","date":"2022-11-26","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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fe7d4321dbeef661","mcp_get_code":{"code_sha256":"fe7d4321dbeef661"}},{"arxiv_id":"2211.05109","paper":"/paper/vitality-unifying-low-rank-and-sparse","title":"ViTALiTy: Unifying Low-rank and Sparse Approximation for Vision Transformer Acceleration with a Linear Taylor Attention","date":"2022-11-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GATECH-EIC/ViTaLiTy","path":"src/drop.py","file_url":"https://github.com/GATECH-EIC/ViTaLiTy/blob/HEAD/src/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f9a1900525331e0f","mcp_get_code":{"code_sha256":"f9a1900525331e0f"}},{"arxiv_id":"2210.06551","paper":"/paper/motionbert-unified-pretraining-for-human","title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","date":"2022-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Walter0807/MotionBERT","path":"lib/model/drop.py","file_url":"https://github.com/Walter0807/MotionBERT/blob/HEAD/lib/model/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2210.06155","paper":"/paper/ernie-layout-layout-knowledge-enhanced-pre","title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","date":"2022-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NormXU/ERNIE-Layout-Pytorch","path":"networks/modeling_erine_layout_extrapolation.py","file_url":"https://github.com/NormXU/ERNIE-Layout-Pytorch/blob/HEAD/networks/modeling_erine_layout_extrapolation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d4c1c406c2087434","mcp_get_code":{"code_sha256":"d4c1c406c2087434"}},{"arxiv_id":"2210.06110","paper":"/paper/uplift-and-upsample-efficient-3d-human-pose","title":"Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers","date":"2022-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"goldbricklemon/uplift-upsample-3dhpe","path":"common/net/vision_transformer.py","file_url":"https://github.com/goldbricklemon/uplift-upsample-3dhpe/blob/HEAD/common/net/vision_transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6aafcfcb574cb205","mcp_get_code":{"code_sha256":"6aafcfcb574cb205"}},{"arxiv_id":"2210.05958","paper":"/paper/bridging-the-gap-between-vision-transformers","title":"Bridging the Gap Between Vision Transformers and Convolutional Neural Networks on Small Datasets","date":"2022-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arieseirack/dhvt","path":"vision_transformer.py","file_url":"https://github.com/arieseirack/dhvt/blob/HEAD/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2210.02808","paper":"/paper/effective-self-supervised-pre-training-on-low","title":"Effective Self-supervised Pre-training on Low-compute Networks without Distillation","date":"2022-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"saic-fi/SSLight","path":"src/sslight/backbone/vision_transformer.py","file_url":"https://github.com/saic-fi/SSLight/blob/HEAD/src/sslight/backbone/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"04e8544d3f2fd61b","mcp_get_code":{"code_sha256":"04e8544d3f2fd61b"}},{"arxiv_id":"2209.09341","paper":"/paper/a-simple-and-powerful-global-optimization-for","title":"A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation","date":"2022-09-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ponimatkin/ssl-vos","path":"vision_transformer.py","file_url":"https://github.com/ponimatkin/ssl-vos/blob/HEAD/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2209.03917","paper":"/paper/exploring-target-representations-for-masked","title":"Exploring Target Representations for Masked Autoencoders","date":"2022-09-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuxingbin/dbot","path":"evaluation/models.py","file_url":"https://github.com/liuxingbin/dbot/blob/HEAD/evaluation/models.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2208.13721","paper":"/paper/countr-transformer-based-generalised-visual","title":"CounTR: Transformer-based Generalised Visual Counting","date":"2022-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Verg-Avesta/CounTR","path":"models_crossvit.py","file_url":"https://github.com/Verg-Avesta/CounTR/blob/HEAD/models_crossvit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e3aa4e8e74369506","mcp_get_code":{"code_sha256":"e3aa4e8e74369506"}},{"arxiv_id":"2208.13049","paper":"/paper/trojvit-trojan-insertion-in-vision","title":"TrojViT: Trojan Insertion in Vision Transformers","date":"2022-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mxzheng/trojvit","path":"models/drop.py","file_url":"https://github.com/mxzheng/trojvit/blob/HEAD/models/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2208.02541","paper":"/paper/mvsformer-learning-robust-image","title":"MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depth","date":"2022-08-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ewrfcas/mvsformer","path":"models/vision_transformer.py","file_url":"https://github.com/ewrfcas/mvsformer/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2207.02505","paper":"/paper/pure-transformers-are-powerful-graph-learners","title":"Pure Transformers are Powerful Graph Learners","date":"2022-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jw9730/tokengt","path":"large-scale-regression/tokengt/modules/droppath.py","file_url":"https://github.com/jw9730/tokengt/blob/HEAD/large-scale-regression/tokengt/modules/droppath.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"49eae9f4f9e2a885","mcp_get_code":{"code_sha256":"49eae9f4f9e2a885"}},{"arxiv_id":"2207.00579","paper":"/paper/video-clip-baseline-for-ego4d-long-term","title":"Video + CLIP Baseline for Ego4D Long-term Action Anticipation","date":"2022-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"srijandas07/clip_baseline_lta_ego4d","path":"ego4d/models/video_model_builder.py","file_url":"https://github.com/srijandas07/clip_baseline_lta_ego4d/blob/HEAD/ego4d/models/video_model_builder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bcc1cdae3bb3212c","mcp_get_code":{"code_sha256":"bcc1cdae3bb3212c"}},{"arxiv_id":"2206.13188","paper":"/paper/self-supervised-learning-in-remote-sensing-a","title":"Self-supervised Learning in Remote Sensing: A Review","date":"2022-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2206.05184","paper":"/paper/exploring-feature-self-relation-for-self","title":"SERE: Exploring Feature Self-relation for Self-supervised Transformer","date":"2022-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2206.04673","paper":"/paper/neural-prompt-search","title":"Neural Prompt Search","date":"2022-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhangYuanhan-AI/NOAH","path":"model/utils.py","file_url":"https://github.com/ZhangYuanhan-AI/NOAH/blob/HEAD/model/utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"arxiv_id":"2206.02146","paper":"/paper/recurrent-video-restoration-transformer-with","title":"Recurrent Video Restoration Transformer with Guided Deformable Attention","date":"2022-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"labshuhanggu/mia-vsr","path":"archs/mia_sliding_arch.py","file_url":"https://github.com/labshuhanggu/mia-vsr/blob/HEAD/archs/mia_sliding_arch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"52d96aa31ed74a56","mcp_get_code":{"code_sha256":"52d96aa31ed74a56"}},{"arxiv_id":"2205.10203","paper":"/paper/learning-to-count-anything-reference-less","title":"Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision","date":"2022-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"activevisionlab/learningtocountanything","path":"models/backbone_convnext.py","file_url":"https://github.com/activevisionlab/learningtocountanything/blob/HEAD/models/backbone_convnext.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e3aa4e8e74369506","mcp_get_code":{"code_sha256":"e3aa4e8e74369506"}},{"arxiv_id":"2205.03892","paper":"/paper/convmae-masked-convolution-meets-masked","title":"ConvMAE: Masked Convolution Meets Masked Autoencoders","date":"2022-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alpha-vl/convmae","path":"DET/models/convmae.py","file_url":"https://github.com/alpha-vl/convmae/blob/HEAD/DET/models/convmae.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"52eff09408f9308d","mcp_get_code":{"code_sha256":"52eff09408f9308d"}},{"arxiv_id":"2204.13101","paper":"/paper/self-supervised-learning-of-object-parts-for","title":"Self-Supervised Learning of Object Parts for Semantic Segmentation","date":"2022-04-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MkuuWaUjinga/leopart","path":"src/vit.py","file_url":"https://github.com/MkuuWaUjinga/leopart/blob/HEAD/src/vit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2204.08680","paper":"/paper/not-all-tokens-are-equal-human-centric-visual","title":"Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer","date":"2022-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zengwang430521/tcformer","path":"tcformer_module/transformer_utils.py","file_url":"https://github.com/zengwang430521/tcformer/blob/HEAD/tcformer_module/transformer_utils.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":"9d3c18b6f3ac3dc1","mcp_get_code":{"code_sha256":"9d3c18b6f3ac3dc1"}},{"arxiv_id":"2204.07305","paper":"/paper/pushing-the-limits-of-simple-pipelines-for","title":"Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference","date":"2022-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hushell/pmf_cvpr22","path":"models/vision_transformer.py","file_url":"https://github.com/hushell/pmf_cvpr22/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2204.03444","paper":"/paper/deep-visual-geo-localization-benchmark","title":"Deep Visual Geo-localization Benchmark","date":"2022-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gmberton/deep-visual-geo-localization-benchmark","path":"model/cct/stochastic_depth.py","file_url":"https://github.com/gmberton/deep-visual-geo-localization-benchmark/blob/HEAD/model/cct/stochastic_depth.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6bb7492655ecbda4","mcp_get_code":{"code_sha256":"6bb7492655ecbda4"}},{"arxiv_id":"2204.01697","paper":"/paper/maxvit-multi-axis-vision-transformer","title":"MaxViT: Multi-Axis Vision Transformer","date":"2022-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qwopqwop200/MaxVIT-pytorch","path":"MaxVIT.py","file_url":"https://github.com/qwopqwop200/MaxVIT-pytorch/blob/HEAD/MaxVIT.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"arxiv_id":"2203.16250","paper":"/paper/pp-yoloe-an-evolved-version-of-yolo","title":"PP-YOLOE: An evolved version of YOLO","date":"2022-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Nioolek/PPYOLOE_pytorch","path":"ppyoloe/models/drop.py","file_url":"https://github.com/Nioolek/PPYOLOE_pytorch/blob/HEAD/ppyoloe/models/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"arxiv_id":"2203.14415","paper":"/paper/mugs-a-multi-granular-self-supervised","title":"Mugs: A Multi-Granular Self-Supervised Learning Framework","date":"2022-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/mugs","path":"src/vision_transformer.py","file_url":"https://github.com/sail-sg/mugs/blob/HEAD/src/vision_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":"793f2b6524ba26f0","mcp_get_code":{"code_sha256":"793f2b6524ba26f0"}},{"arxiv_id":"2203.12614","paper":"/paper/unsupervised-salient-object-detection-with","title":"Unsupervised Salient Object Detection with Spectral Cluster Voting","date":"2022-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"noelshin/selfmask","path":"networks/vision_transformer.py","file_url":"https://github.com/noelshin/selfmask/blob/HEAD/networks/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"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":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"52d96aa31ed74a56","mcp_get_code":{"code_sha256":"52d96aa31ed74a56"}},{"arxiv_id":"2203.10541","paper":"/paper/unsupervised-domain-adaptation-for-nighttime","title":"Unsupervised Domain Adaptation for Nighttime Aerial Tracking","date":"2022-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vision4robotics/UDAT","path":"UDAT/BAN/siamban/models/trans_discriminator.py","file_url":"https://github.com/vision4robotics/UDAT/blob/HEAD/UDAT/BAN/siamban/models/trans_discriminator.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2203.10233","paper":"/paper/direcformer-a-directed-attention-in","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","date":"2022-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uark-cviu/direcformer","path":"slowfast/models/common.py","file_url":"https://github.com/uark-cviu/direcformer/blob/HEAD/slowfast/models/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"bcc1cdae3bb3212c","mcp_get_code":{"code_sha256":"bcc1cdae3bb3212c"}},{"arxiv_id":"2203.08414","paper":"/paper/unsupervised-semantic-segmentation-by-2","title":"Unsupervised Semantic Segmentation by Distilling Feature Correspondences","date":"2022-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leggedrobotics/self_supervised_segmentation","path":"stego/backbones/dino/vision_transformer.py","file_url":"https://github.com/leggedrobotics/self_supervised_segmentation/blob/HEAD/stego/backbones/dino/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2203.08392","paper":"/paper/patch-fool-are-vision-transformers-always-1","title":"Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?","date":"2022-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RICE-EIC/Patch-Fool","path":"models/drop.py","file_url":"https://github.com/RICE-EIC/Patch-Fool/blob/HEAD/models/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2202.11929","paper":"/paper/word-segmentation-on-discovered-phone-units","title":"Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring","date":"2022-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jasonppy/word-discovery","path":"models/vision_transformer.py","file_url":"https://github.com/jasonppy/word-discovery/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2202.07800","paper":"/paper/not-all-patches-are-what-you-need-expediting","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","date":"2022-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"youweiliang/evit","path":"evit.py","file_url":"https://github.com/youweiliang/evit/blob/HEAD/evit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"arxiv_id":"2202.00874","paper":"/paper/hts-at-a-hierarchical-token-semantic-audio","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","date":"2022-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"retrocirce/hts-audio-transformer","path":"model/layers.py","file_url":"https://github.com/retrocirce/hts-audio-transformer/blob/HEAD/model/layers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2201.12288","paper":"/paper/vrt-a-video-restoration-transformer","title":"VRT: A Video Restoration Transformer","date":"2022-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jingyunliang/vrt","path":"models/network_vrt.py","file_url":"https://github.com/jingyunliang/vrt/blob/HEAD/models/network_vrt.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"9ea4d5b8b4d5ef2f","mcp_get_code":{"code_sha256":"9ea4d5b8b4d5ef2f"}},{"arxiv_id":"2201.11095","paper":"/paper/self-attention-fusion-for-audiovisual-emotion","title":"Self-attention fusion for audiovisual emotion recognition with incomplete data","date":"2022-01-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"katerynaCh/multimodal-emotion-recognition","path":"models/transformer_timm.py","file_url":"https://github.com/katerynaCh/multimodal-emotion-recognition/blob/HEAD/models/transformer_timm.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"743bf392200483a3","mcp_get_code":{"code_sha256":"743bf392200483a3"}},{"arxiv_id":"2201.02609","paper":"/paper/generalized-category-discovery","title":"Generalized Category Discovery","date":"2022-01-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sgvaze/generalized-category-discovery","path":"models/vision_transformer.py","file_url":"https://github.com/sgvaze/generalized-category-discovery/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2112.14000","paper":"/paper/pale-transformer-a-general-vision-transformer","title":"Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention","date":"2021-12-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qwopqwop200/pale-transformer-pytorch","path":"pale-transformer.py","file_url":"https://github.com/qwopqwop200/pale-transformer-pytorch/blob/HEAD/pale-transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"arxiv_id":"2112.05425","paper":"/paper/couplformer-rethinking-vision-transformer","title":"Couplformer:Rethinking Vision Transformer with Coupling Attention Map","date":"2021-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wer010/Couplformer","path":"src/utils/stochastic_depth.py","file_url":"https://github.com/wer010/Couplformer/blob/HEAD/src/utils/stochastic_depth.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6bb7492655ecbda4","mcp_get_code":{"code_sha256":"6bb7492655ecbda4"}},{"arxiv_id":"2111.12958","paper":"/paper/self-distilled-self-supervised-representation","title":"Self-Distilled Self-Supervised Representation Learning","date":"2021-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hagiss/sdssl","path":"vision_transformer.py","file_url":"https://github.com/hagiss/sdssl/blob/HEAD/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2111.09887","paper":"/paper/pytorchvideo-a-deep-learning-library-for","title":"PyTorchVideo: A Deep Learning Library for Video Understanding","date":"2021-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/pytorchvideo","path":"pytorchvideo/layers/drop_path.py","file_url":"https://github.com/facebookresearch/pytorchvideo/blob/HEAD/pytorchvideo/layers/drop_path.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"3eb98239357e3133","mcp_get_code":{"code_sha256":"3eb98239357e3133"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3c83cad222232ac6","mcp_get_code":{"code_sha256":"3c83cad222232ac6"}},{"arxiv_id":"2110.07719","paper":"/paper/certified-patch-robustness-via-smoothed-1","title":"Certified Patch Robustness via Smoothed Vision Transformers","date":"2021-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"madrylab/smoothed-vit","path":"src/utils/custom_models/layers/drop.py","file_url":"https://github.com/madrylab/smoothed-vit/blob/HEAD/src/utils/custom_models/layers/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2110.07058","paper":"/paper/ego4d-around-the-world-in-3000-hours-of","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","date":"2021-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ego4d/forecasting","path":"ego4d_forecasting/models/video_model_builder.py","file_url":"https://github.com/ego4d/forecasting/blob/HEAD/ego4d_forecasting/models/video_model_builder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bcc1cdae3bb3212c","mcp_get_code":{"code_sha256":"bcc1cdae3bb3212c"}},{"arxiv_id":"2110.06915","paper":"/paper/object-region-video-transformers-1","title":"Object-Region Video Transformers","date":"2021-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eladb3/orvit","path":"slowfast/models/ORViT/orvit.py","file_url":"https://github.com/eladb3/orvit/blob/HEAD/slowfast/models/ORViT/orvit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"bcc1cdae3bb3212c","mcp_get_code":{"code_sha256":"bcc1cdae3bb3212c"}},{"arxiv_id":"2109.13228","paper":"/paper/pass-an-imagenet-replacement-for-self","title":"PASS: An ImageNet replacement for self-supervised pretraining without humans","date":"2021-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/dino","path":"vision_transformer.py","file_url":"https://github.com/facebookresearch/dino/blob/HEAD/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2109.08472","paper":"/paper/actionclip-a-new-paradigm-for-video-action","title":"ActionCLIP: A New Paradigm for Video Action Recognition","date":"2021-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sallymmx/actionclip","path":"clip/model.py","file_url":"https://github.com/sallymmx/actionclip/blob/HEAD/clip/model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2109.02038","paper":"/paper/nas-ood-neural-architecture-search-for-out-of","title":"NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization","date":"2021-09-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HaoyueBaiZJU/NAS-OoD","path":"nas_ood_single/search/models/model_search.py","file_url":"https://github.com/HaoyueBaiZJU/NAS-OoD/blob/HEAD/nas_ood_single/search/models/model_search.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b1286732acea8936","mcp_get_code":{"code_sha256":"b1286732acea8936"}},{"arxiv_id":"2108.11084","paper":"/paper/efficient-transformer-for-single-image-super","title":"Transformer for Single Image Super-Resolution","date":"2021-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luissen/esrt","path":"util/transformer.py","file_url":"https://github.com/luissen/esrt/blob/HEAD/util/transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"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":"XPixelGroup/BasicSR","path":"basicsr/archs/swinir_arch.py","file_url":"https://github.com/XPixelGroup/BasicSR/blob/HEAD/basicsr/archs/swinir_arch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"52d96aa31ed74a56","mcp_get_code":{"code_sha256":"52d96aa31ed74a56"}},{"arxiv_id":"2108.05045","paper":"/paper/semi-supervised-domain-generalizable-person","title":"Semi-Supervised Domain Generalizable Person Re-Identification","date":"2021-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"L1aoXingyu/reid_baseline","path":"fastreid/layers/drop.py","file_url":"https://github.com/L1aoXingyu/reid_baseline/blob/HEAD/fastreid/layers/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2107.00644","paper":"/paper/stabilizing-deep-q-learning-with-convnets-and","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","date":"2021-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nicklashansen/svea-vit","path":"src/algorithms/layers/drop.py","file_url":"https://github.com/nicklashansen/svea-vit/blob/HEAD/src/algorithms/layers/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"arxiv_id":"2106.09703","paper":"/paper/modist-motion-distillation-for-self","title":"MaCLR: Motion-aware Contrastive Learning of Representations for Videos","date":"2021-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/self-supervised-maclr","path":"slowfast/models/common.py","file_url":"https://github.com/amazon-science/self-supervised-maclr/blob/HEAD/slowfast/models/common.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":"bcc1cdae3bb3212c","mcp_get_code":{"code_sha256":"bcc1cdae3bb3212c"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0233d6e8a07784ae","mcp_get_code":{"code_sha256":"0233d6e8a07784ae"}},{"arxiv_id":"2106.00666","paper":"/paper/you-only-look-at-one-sequence-rethinking","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","date":"2021-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hustvl/YOLOS","path":"models/layers/drop.py","file_url":"https://github.com/hustvl/YOLOS/blob/HEAD/models/layers/drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"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":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"2104.14222","paper":"/paper/privacy-preserving-portrait-matting","title":"Privacy-Preserving Portrait Matting","date":"2021-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucaspk512/vrdone","path":"models/blocks.py","file_url":"https://github.com/lucaspk512/vrdone/blob/HEAD/models/blocks.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a34c005ba2203f35","mcp_get_code":{"code_sha256":"a34c005ba2203f35"}},{"arxiv_id":"2104.12533","paper":"/paper/visformer-the-vision-friendly-transformer","title":"Visformer: The Vision-friendly Transformer","date":"2021-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"danczs/Visformer","path":"models.py","file_url":"https://github.com/danczs/Visformer/blob/HEAD/models.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2104.09770","paper":"/paper/m2tr-multi-modal-multi-scale-transformers-for","title":"M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection","date":"2021-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangjk666/PyDeepFakeDet","path":"PyDeepFakeDet/models/vit.py","file_url":"https://github.com/wangjk666/PyDeepFakeDet/blob/HEAD/PyDeepFakeDet/models/vit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"arxiv_id":"2103.15798","paper":"/paper/rethinking-neural-operations-for-diverse","title":"Rethinking Neural Operations for Diverse Tasks","date":"2021-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nick11roberts/XD","path":"DARTS/utils.py","file_url":"https://github.com/nick11roberts/XD/blob/HEAD/DARTS/utils.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":"13c2719404e25b25","mcp_get_code":{"code_sha256":"13c2719404e25b25"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2ec78252af199d14","mcp_get_code":{"code_sha256":"2ec78252af199d14"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"91cff3d019791354","mcp_get_code":{"code_sha256":"91cff3d019791354"}},{"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":"1fcf8df260e4c014","mcp_get_code":{"code_sha256":"1fcf8df260e4c014"}},{"arxiv_id":"2103.13258","paper":"/paper/dynamic-slimmable-network","title":"Dynamic Slimmable Network","date":"2021-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"changlin31/DS-Net","path":"dyn_slim/models/dyn_slim_net.py","file_url":"https://github.com/changlin31/DS-Net/blob/HEAD/dyn_slim/models/dyn_slim_net.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a86440e38234fea6","mcp_get_code":{"code_sha256":"a86440e38234fea6"}},{"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":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"971ae8d2d8313e30","mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6bb7492655ecbda4","mcp_get_code":{"code_sha256":"6bb7492655ecbda4"}},{"arxiv_id":"2007.09384","paper":"/paper/multi-scale-positive-sample-refinement-for","title":"Multi-Scale Positive Sample Refinement for Few-Shot Object Detection","date":"2020-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bohao-lee/pdc","path":"models/vision_transformer.py","file_url":"https://github.com/bohao-lee/pdc/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2007.03331","paper":"/paper/gold-nas-gradual-one-level-differentiable","title":"GOLD-NAS: Gradual, One-Level, Differentiable","date":"2020-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sunsmarterjie/GOLD_NAS","path":"cifar_search/utils.py","file_url":"https://github.com/sunsmarterjie/GOLD_NAS/blob/HEAD/cifar_search/utils.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":"13c2719404e25b25","mcp_get_code":{"code_sha256":"13c2719404e25b25"}},{"arxiv_id":"2007.03154","paper":"/paper/discretization-aware-architecture-search","title":"Discretization-Aware Architecture Search","date":"2020-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sunsmarterjie/DAAS","path":"cnn/utils.py","file_url":"https://github.com/sunsmarterjie/DAAS/blob/HEAD/cnn/utils.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":"13c2719404e25b25","mcp_get_code":{"code_sha256":"13c2719404e25b25"}},{"arxiv_id":"2006.16537","paper":"/paper/theory-inspired-path-regularized-differential","title":"Theory-Inspired Path-Regularized Differential Network Architecture Search","date":"2020-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/PR-DARTS","path":"PRDARTS_eval/utils.py","file_url":"https://github.com/salesforce/PR-DARTS/blob/HEAD/PRDARTS_eval/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"13c2719404e25b25","mcp_get_code":{"code_sha256":"13c2719404e25b25"}},{"arxiv_id":"2006.06863","paper":"/paper/few-shot-neural-architecture-search","title":"Few-shot Neural Architecture Search","date":"2020-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aoiang/few-shot-NAS","path":"Few-Shot-NAS_cifar10/model.py","file_url":"https://github.com/aoiang/few-shot-NAS/blob/HEAD/Few-Shot-NAS_cifar10/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2b74f4d9967cbb59","mcp_get_code":{"code_sha256":"2b74f4d9967cbb59"}},{"arxiv_id":"1912.00195","paper":"/paper/sgas-sequential-greedy-architecture-search","title":"SGAS: Sequential Greedy Architecture Search","date":"2019-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lightaime/sgas","path":"cnn/utils.py","file_url":"https://github.com/lightaime/sgas/blob/HEAD/cnn/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"13c2719404e25b25","mcp_get_code":{"code_sha256":"13c2719404e25b25"}},{"arxiv_id":"1912.00195","paper":"/paper/sgas-sequential-greedy-architecture-search","title":"SGAS: Sequential Greedy Architecture Search","date":"2019-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lightaime/sgas","path":"gcn/gcn_graph/model.py","file_url":"https://github.com/lightaime/sgas/blob/HEAD/gcn/gcn_graph/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a8c6a004344526a2","mcp_get_code":{"code_sha256":"a8c6a004344526a2"}},{"arxiv_id":"1907.05737","paper":"/paper/pc-darts-partial-channel-connections-for","title":"PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search","date":"2019-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"peteryuX/pcdarts-tf2","path":"modules/operations.py","file_url":"https://github.com/peteryuX/pcdarts-tf2/blob/HEAD/modules/operations.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"62658d26ba90a118","mcp_get_code":{"code_sha256":"62658d26ba90a118"}},{"arxiv_id":"1906.01502","paper":"/paper/how-multilingual-is-multilingual-bert","title":"How multilingual is Multilingual BERT?","date":"2019-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ku21fan/cll-str","path":"modules/svtr.py","file_url":"https://github.com/ku21fan/cll-str/blob/HEAD/modules/svtr.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e3aa4e8e74369506","mcp_get_code":{"code_sha256":"e3aa4e8e74369506"}},{"arxiv_id":"1806.09055","paper":"/paper/darts-differentiable-architecture-search","title":"DARTS: Differentiable Architecture Search","date":"2018-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"quark0/darts","path":"cnn/utils.py","file_url":"https://github.com/quark0/darts/blob/HEAD/cnn/utils.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":"13c2719404e25b25","mcp_get_code":{"code_sha256":"13c2719404e25b25"}},{"arxiv_id":"1802.03268","paper":"/paper/efficient-neural-architecture-search-via-1","title":"Efficient Neural Architecture Search via Parameter Sharing","date":"2018-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaileymonn/Quantized-ENAS-ConvNets","path":"micro_child.py","file_url":"https://github.com/kaileymonn/Quantized-ENAS-ConvNets/blob/HEAD/micro_child.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"04864e18c26d7b4a","mcp_get_code":{"code_sha256":"04864e18c26d7b4a"}},{"arxiv_id":"openreview_eDlsO4kFaX","paper":null,"title":"arXiv:openreview_eDlsO4kFaX","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"KiiSooo/CODiff","path":"dinov2/layers/drop_path.py","file_url":"https://github.com/KiiSooo/CODiff/blob/HEAD/dinov2/layers/drop_path.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c157f5b112b3a392","mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"arxiv_id":"openreview_YA3AvVx2Ze","paper":null,"title":"arXiv:openreview_YA3AvVx2Ze","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"lytang63/CoGe-GCD","path":"models/vision_transformer.py","file_url":"https://github.com/lytang63/CoGe-GCD/blob/HEAD/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"openreview_OdrEcfMogy","paper":null,"title":"arXiv:openreview_OdrEcfMogy","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"YuanGao-YG/OneForecast","path":"models/Fengwu.py","file_url":"https://github.com/YuanGao-YG/OneForecast/blob/HEAD/models/Fengwu.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6e64c5588151abd3","mcp_get_code":{"code_sha256":"6e64c5588151abd3"}},{"arxiv_id":"openreview_GNrBEnHPPv","paper":null,"title":"arXiv:openreview_GNrBEnHPPv","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Gang-ww/ABFnet","path":"maxpha_v47_token_v1.py","file_url":"https://github.com/Gang-ww/ABFnet/blob/HEAD/maxpha_v47_token_v1.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"73d573cd83d247e0","mcp_get_code":{"code_sha256":"73d573cd83d247e0"}},{"arxiv_id":"aaai_29368","paper":null,"title":"arXiv:aaai_29368","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zibinpan/FedLF","path":"gfedplat/model/CCT.py","file_url":"https://github.com/zibinpan/FedLF/blob/HEAD/gfedplat/model/CCT.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"af70f775dccf6644","mcp_get_code":{"code_sha256":"af70f775dccf6644"}},{"arxiv_id":"aaai_28502","paper":null,"title":"arXiv:aaai_28502","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"yuhongtian17/Spatial-Transform-Decoupling","path":"mmrotate-main/models/vision_transformer.py","file_url":"https://github.com/yuhongtian17/Spatial-Transform-Decoupling/blob/HEAD/mmrotate-main/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"aaai_28322","paper":null,"title":"arXiv:aaai_28322","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"tsj-001/AAAI24-GKT","path":"gkt/model_bank/cait_ddp.py","file_url":"https://github.com/tsj-001/AAAI24-GKT/blob/HEAD/gkt/model_bank/cait_ddp.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f3c67c589b630c22","mcp_get_code":{"code_sha256":"f3c67c589b630c22"}},{"arxiv_id":"aaai_28092","paper":null,"title":"arXiv:aaai_28092","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"lhf12278/FCM-ReID","path":"clustercontrast/models/vision_transformer.py","file_url":"https://github.com/lhf12278/FCM-ReID/blob/HEAD/clustercontrast/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"arxiv_id":"aaai_25395","paper":null,"title":"arXiv:aaai_25395","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Quinn777/CAP","path":"models/vit/visformer.py","file_url":"https://github.com/Quinn777/CAP/blob/HEAD/models/vit/visformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"Zhou_Towards_Effective_Foundation_Model_Adaptation_for_Extreme_Cross-Domain_Few-Shot_Learning_ICCV_2025_paper","paper":null,"title":"arXiv:Zhou_Towards_Effective_Foundation_Model_Adaptation_for_Extreme_Cross-Domain_Few-Shot_Learning_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"NWPUZhoufei/FMA","path":"vision_transformer.py","file_url":"https://github.com/NWPUZhoufei/FMA/blob/HEAD/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"Zhang_TokenHPE_Learning_Orientation_Tokens_for_Efficient_Head_Pose_Estimation_via_CVPR_2023_paper","paper":null,"title":"arXiv:Zhang_TokenHPE_Learning_Orientation_Tokens_for_Efficient_Head_Pose_Estimation_via_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zc2023/TokenHPE","path":"ViT_model.py","file_url":"https://github.com/zc2023/TokenHPE/blob/HEAD/ViT_model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fe7d4321dbeef661","mcp_get_code":{"code_sha256":"fe7d4321dbeef661"}},{"arxiv_id":"Zhang_Enhancing_Zero-shot_Object_Counting_via_Text-guided_Local_Ranking_and_Number-evoked_ICCV_2025_paper","paper":null,"title":"arXiv:Zhang_Enhancing_Zero-shot_Object_Counting_via_Text-guided_Local_Ranking_and_Number-evoked_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zaqai/LGCount","path":"models/models_crossvit.py","file_url":"https://github.com/zaqai/LGCount/blob/HEAD/models/models_crossvit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e3aa4e8e74369506","mcp_get_code":{"code_sha256":"e3aa4e8e74369506"}},{"arxiv_id":"Wang_Deep_Arbitrary-Scale_Image_Super-Resolution_via_Scale-Equivariance_Pursuit_CVPR_2023_paper","paper":null,"title":"arXiv:Wang_Deep_Arbitrary-Scale_Image_Super-Resolution_via_Scale-Equivariance_Pursuit_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"neuralchen/EQSR","path":"EQSR/archs/hat_ModMBFormer_Sim_arch.py","file_url":"https://github.com/neuralchen/EQSR/blob/HEAD/EQSR/archs/hat_ModMBFormer_Sim_arch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"52d96aa31ed74a56","mcp_get_code":{"code_sha256":"52d96aa31ed74a56"}},{"arxiv_id":"Wang_Deep_Arbitrary-Scale_Image_Super-Resolution_via_Scale-Equivariance_Pursuit_CVPR_2023_paper","paper":null,"title":"arXiv:Wang_Deep_Arbitrary-Scale_Image_Super-Resolution_via_Scale-Equivariance_Pursuit_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"neuralchen/EQSR","path":"EQSR/archs/hat_arch.py","file_url":"https://github.com/neuralchen/EQSR/blob/HEAD/EQSR/archs/hat_arch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9ea4d5b8b4d5ef2f","mcp_get_code":{"code_sha256":"9ea4d5b8b4d5ef2f"}},{"arxiv_id":"Tiong_Flexible_Biometrics_Recognition_Bridging_the_Multimodality_Gap_through_Attention_Alignment_CVPR_2024_paper","paper":null,"title":"arXiv:Tiong_Flexible_Biometrics_Recognition_Bridging_the_Multimodality_Gap_through_Attention_Alignment_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"MIS-DevWorks/FBR","path":"models/regularizer.py","file_url":"https://github.com/MIS-DevWorks/FBR/blob/HEAD/models/regularizer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"Sun_Pixel-level_Semantic_Correspondence_through_Layout-aware_Representation_Learning_and_Multi-scale_Matching_CVPR_2024_paper","paper":null,"title":"arXiv:Sun_Pixel-level_Semantic_Correspondence_through_Layout-aware_Representation_Learning_and_Multi-scale_Matching_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"YXSUNMADMAX/LPMFlow","path":"models/feature_backbones/vision_transformer.py","file_url":"https://github.com/YXSUNMADMAX/LPMFlow/blob/HEAD/models/feature_backbones/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"Lu_FedHCA2_Towards_Hetero-Client_Federated_Multi-Task_Learning_CVPR_2024_paper","paper":null,"title":"arXiv:Lu_FedHCA2_Towards_Hetero-Client_Federated_Multi-Task_Learning_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"innovator-zero/FedHCA2","path":"models/swin.py","file_url":"https://github.com/innovator-zero/FedHCA2/blob/HEAD/models/swin.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2ec78252af199d14","mcp_get_code":{"code_sha256":"2ec78252af199d14"}},{"arxiv_id":"Li_I-ViT_Integer-only_Quantization_for_Efficient_Vision_Transformer_Inference_ICCV_2023_paper","paper":null,"title":"arXiv:Li_I-ViT_Integer-only_Quantization_for_Efficient_Vision_Transformer_Inference_ICCV_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zkkli/I-ViT","path":"models/layers_quant.py","file_url":"https://github.com/zkkli/I-ViT/blob/HEAD/models/layers_quant.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"Li_FPEM_Face_Prior_Enhanced_Facial_Attractiveness_Prediction_for_Live_Videos_ICCV_2025_paper","paper":null,"title":"arXiv:Li_FPEM_Face_Prior_Enhanced_Facial_Attractiveness_Prediction_for_Live_Videos_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Estella-LH/FPEM","path":"nets/VIT.py","file_url":"https://github.com/Estella-LH/FPEM/blob/HEAD/nets/VIT.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fe7d4321dbeef661","mcp_get_code":{"code_sha256":"fe7d4321dbeef661"}},{"arxiv_id":"Huang_AnomalyNCD_Towards_Novel_Anomaly_Class_Discovery_in_Industrial_Scenarios_CVPR_2025_paper","paper":null,"title":"arXiv:Huang_AnomalyNCD_Towards_Novel_Anomaly_Class_Discovery_in_Industrial_Scenarios_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"HUST-SLOW/AnomalyNCD","path":"models/modules/_MGViT.py","file_url":"https://github.com/HUST-SLOW/AnomalyNCD/blob/HEAD/models/modules/_MGViT.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"Gao_Bootstrapping_SparseFormers_from_Vision_Foundation_Models_CVPR_2024_paper","paper":null,"title":"arXiv:Gao_Bootstrapping_SparseFormers_from_Vision_Foundation_Models_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"showlab/sparseformer","path":"imagenet/models/sparseformer.py","file_url":"https://github.com/showlab/sparseformer/blob/HEAD/imagenet/models/sparseformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f25fe96cae14da8c","mcp_get_code":{"code_sha256":"f25fe96cae14da8c"}},{"arxiv_id":"Gao_Bootstrapping_SparseFormers_from_Vision_Foundation_Models_CVPR_2024_paper","paper":null,"title":"arXiv:Gao_Bootstrapping_SparseFormers_from_Vision_Foundation_Models_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"showlab/sparseformer","path":"sparseformer/sparseformer/utils.py","file_url":"https://github.com/showlab/sparseformer/blob/HEAD/sparseformer/sparseformer/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d456d4ee3b5b84d7","mcp_get_code":{"code_sha256":"d456d4ee3b5b84d7"}},{"arxiv_id":"Fang_Unleashing_Vanilla_Vision_Transformer_with_Masked_Image_Modeling_for_Object_ICCV_2023_paper","paper":null,"title":"arXiv:Fang_Unleashing_Vanilla_Vision_Transformer_with_Masked_Image_Modeling_for_Object_ICCV_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"hustvl/MIMDet","path":"models/benchmarking.py","file_url":"https://github.com/hustvl/MIMDet/blob/HEAD/models/benchmarking.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"52eff09408f9308d","mcp_get_code":{"code_sha256":"52eff09408f9308d"}},{"arxiv_id":"Du_On-the-Fly_Category_Discovery_CVPR_2023_paper","paper":null,"title":"arXiv:Du_On-the-Fly_Category_Discovery_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"PRIS-CV/On-the-fly-Category-Discovery","path":"vision_transformer.py","file_url":"https://github.com/PRIS-CV/On-the-fly-Category-Discovery/blob/HEAD/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"2024.findings-acl.747","paper":null,"title":"arXiv:2024.findings-acl.747","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"whwu95/Text4Vis","path":"clip/model.py","file_url":"https://github.com/whwu95/Text4Vis/blob/HEAD/clip/model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac6b7d76e8e3584","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"arxiv_id":"136950068","paper":null,"title":"arXiv:136950068","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"wangjk666/STTS","path":"MViT/slowfast/models/common.py","file_url":"https://github.com/wangjk666/STTS/blob/HEAD/MViT/slowfast/models/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bcc1cdae3bb3212c","mcp_get_code":{"code_sha256":"bcc1cdae3bb3212c"}},{"arxiv_id":"136810551","paper":null,"title":"arXiv:136810551","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"YtongXie/UniMiSS-code","path":"UniMiSS/models/MiT.py","file_url":"https://github.com/YtongXie/UniMiSS-code/blob/HEAD/UniMiSS/models/MiT.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55120f2026b56aa2","mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"arxiv_id":"136740192","paper":null,"title":"arXiv:136740192","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"CASIA-IVA-Lab/PASS-reID","path":"PASS_cluster_contrast_reid/clustercontrast/models/vision_transformer.py","file_url":"https://github.com/CASIA-IVA-Lab/PASS-reID/blob/HEAD/PASS_cluster_contrast_reid/clustercontrast/models/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"39eace7e2822504f","mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"arxiv_id":"04820","paper":null,"title":"arXiv:04820","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Kelly510/PoseRetNet","path":"common/model/droppath.py","file_url":"https://github.com/Kelly510/PoseRetNet/blob/HEAD/common/model/droppath.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87577b3ff9d32712","mcp_get_code":{"code_sha256":"87577b3ff9d32712"}}]}