{"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/build-transform","entry":"build_transform","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":170,"n_papers_ran":82,"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":69,"n_samples_ran":27,"n_samples_fingerprinted":0,"n_places":172,"n_places_pointer_only":58,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":27,"unverified":42},"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":"2606.16158","paper":"/paper/arxiv-2606-16158","title":"Focus When Necessary: Adaptive Routing and Collaborative Grounding for Training-Free Visual Grounding","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"TencentBAC/LazyMCoT","path":"Internvl/utiles_internvl.py","file_url":"https://github.com/TencentBAC/LazyMCoT/blob/HEAD/Internvl/utiles_internvl.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":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2606.07289","paper":"/paper/arxiv-2606-07289","title":"Closed-Form Spectral Regularization for Multi-Task Model Merging","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"WalkerWorldPeace/MLLMerging","path":"InternVL/internvl_chat/model_merging.py","file_url":"https://github.com/WalkerWorldPeace/MLLMerging/blob/HEAD/InternVL/internvl_chat/model_merging.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2605.31351","paper":"/paper/arxiv-2605-31351","title":"VIABLE: A Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"YiyiyiZhao/VIABLE","path":"viable/run_effectiveness/judge_infer_direct/utils_effectiveness/inference_internvl.py","file_url":"https://github.com/YiyiyiZhao/VIABLE/blob/HEAD/viable/run_effectiveness/judge_infer_direct/utils_effectiveness/inference_internvl.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f0e0c861b89dbe01","mcp_get_code":{"code_sha256":"f0e0c861b89dbe01"}},{"arxiv_id":"2605.24770","paper":"/paper/arxiv-2605-24770","title":"Muon in Vision Transformers: Optimizer-Recipe Interactions and Gradient Spectra","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"facebookresearch/mae","path":"util/datasets.py","file_url":"https://github.com/facebookresearch/mae/blob/HEAD/util/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"800cebf161a8aa26","mcp_get_code":{"code_sha256":"800cebf161a8aa26"}},{"arxiv_id":"2605.00273","paper":"/paper/arxiv-2605-00273","title":"When Do Diffusion Models Learn to Generate Multiple Objects?","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"eugene6923/MOSAIC","path":"mosaic/comfort_utils/model_utils/intern_vl.py","file_url":"https://github.com/eugene6923/MOSAIC/blob/HEAD/mosaic/comfort_utils/model_utils/intern_vl.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8cf510a10c5f26c3","mcp_get_code":{"code_sha256":"8cf510a10c5f26c3"}},{"arxiv_id":"2603.00515","paper":"/paper/arxiv-2603-00515","title":"MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"GVCLab/MLLM-4D","path":"evaluation/model_inference/internvideo2_5.py","file_url":"https://github.com/GVCLab/MLLM-4D/blob/HEAD/evaluation/model_inference/internvideo2_5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8e7f5895ff4790f2","mcp_get_code":{"code_sha256":"8e7f5895ff4790f2"}},{"arxiv_id":"2602.01219","paper":"/paper/arxiv-2602-01219","title":"Mixture-of-Top-k Attention: Efficient Attention via Scalable Fast Weights","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"QishuaiWen/MiTA","path":"MiTA-DeiT/datasets.py","file_url":"https://github.com/QishuaiWen/MiTA/blob/HEAD/MiTA-DeiT/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ebeb7b6e20a434cf","mcp_get_code":{"code_sha256":"ebeb7b6e20a434cf"}},{"arxiv_id":"2601.15888","paper":"/paper/arxiv-2601-15888","title":"Understanding the Transfer Limits of Vision Foundation Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"pimed/ProViCNet","path":"ProViCNet/ModelArchitectures/LeViTUnet/datasets.py","file_url":"https://github.com/pimed/ProViCNet/blob/HEAD/ProViCNet/ModelArchitectures/LeViTUnet/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2601.06460","paper":"/paper/arxiv-2601-06460","title":"Tone Matters: The Impact of Linguistic Tone on Hallucination in VLMs","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"bli1/tone-matters","path":"VLM_Benchmark_GitHub_Ready/benchmark/model_runners/benchmark_internvl25_freeform_with_judge.py","file_url":"https://github.com/bli1/tone-matters/blob/HEAD/VLM_Benchmark_GitHub_Ready/benchmark/model_runners/benchmark_internvl25_freeform_with_judge.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"348c74308f779a92","mcp_get_code":{"code_sha256":"348c74308f779a92"}},{"arxiv_id":"2511.10648","paper":"/paper/arxiv-2511-10648","title":"Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"GenuineWWD/SCS","path":"evaluation/eval_internvl_m3cot.py","file_url":"https://github.com/GenuineWWD/SCS/blob/HEAD/evaluation/eval_internvl_m3cot.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":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2511.10648","paper":"/paper/arxiv-2511-10648","title":"Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"GenuineWWD/SCS","path":"evaluation/eval_internvl_mathverse.py","file_url":"https://github.com/GenuineWWD/SCS/blob/HEAD/evaluation/eval_internvl_mathverse.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":"f0e0c861b89dbe01","mcp_get_code":{"code_sha256":"f0e0c861b89dbe01"}},{"arxiv_id":"2510.16877","paper":"/paper/arxiv-2510-16877","title":"Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"gfyddha/Fly-CL","path":"datasets/load_dataset.py","file_url":"https://github.com/gfyddha/Fly-CL/blob/HEAD/datasets/load_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bf0b63ed17d26056","mcp_get_code":{"code_sha256":"bf0b63ed17d26056"}},{"arxiv_id":"2510.14605","paper":"/paper/arxiv-2510-14605","title":"Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"om-ai-lab/VLM-R1","path":"src/open-r1-multimodal/src/open_r1/vlm_modules/internvl_module.py","file_url":"https://github.com/om-ai-lab/VLM-R1/blob/HEAD/src/open-r1-multimodal/src/open_r1/vlm_modules/internvl_module.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":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2507.20291","paper":null,"title":"arXiv:2507.20291","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"Joyies/TVT","path":"TVT/my_utils/training_utils_realsr.py","file_url":"https://github.com/Joyies/TVT/blob/HEAD/TVT/my_utils/training_utils_realsr.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"02535e498b20260c","mcp_get_code":{"code_sha256":"02535e498b20260c"}},{"arxiv_id":"2507.17539","paper":null,"title":"arXiv:2507.17539","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"MeteorElf/FundusExpert","path":"src/quick_start.py","file_url":"https://github.com/MeteorElf/FundusExpert/blob/HEAD/src/quick_start.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":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2507.00790","paper":"/paper/ld-rps-zero-shot-unified-image-restoration","title":"LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior Sampling","date":"2025-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AMAP-ML/LD-RPS","path":"get_prompts.py","file_url":"https://github.com/AMAP-ML/LD-RPS/blob/HEAD/get_prompts.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2505.24787","paper":"/paper/draw-all-your-imagine-a-holistic-benchmark","title":"Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generation","date":"2025-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yczhou001/longbench-t2i","path":"utils/evaluator.py","file_url":"https://github.com/yczhou001/longbench-t2i/blob/HEAD/utils/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c577dc3012980327","mcp_get_code":{"code_sha256":"c577dc3012980327"}},{"arxiv_id":"2505.10352","paper":"/paper/spikevideoformer-an-efficient-spike-driven","title":"SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\\mathcal{O}(T)$ Complexity","date":"2025-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jimmyzou/spikevideoformer","path":"classification/dataloader/datasets.py","file_url":"https://github.com/jimmyzou/spikevideoformer/blob/HEAD/classification/dataloader/datasets.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":"88b52105e585902e","mcp_get_code":{"code_sha256":"88b52105e585902e"}},{"arxiv_id":"2504.18397","paper":"/paper/unsupervised-visual-chain-of-thought","title":"Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization","date":"2025-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kesenzhao/uv-cot","path":"omnilmm/model/omnilmm.py","file_url":"https://github.com/kesenzhao/uv-cot/blob/HEAD/omnilmm/model/omnilmm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ce385361217c109c","mcp_get_code":{"code_sha256":"ce385361217c109c"}},{"arxiv_id":"2504.15485","paper":null,"title":"arXiv:2504.15485","date":null,"month_inferred_from_arxiv_id":"2025-04","title_source":null,"repo":"atinpothiraj/CAPTURe","path":"occluded_scripts/intern.py","file_url":"https://github.com/atinpothiraj/CAPTURe/blob/HEAD/occluded_scripts/intern.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2503.23455","paper":"/paper/efficient-token-compression-for-vision","title":"Efficient Token Compression for Vision Transformer with Spatial Information Preserved","date":"2025-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nust-machine-intelligence-laboratory/prune_and_merge","path":"pm-vit/datasets.py","file_url":"https://github.com/nust-machine-intelligence-laboratory/prune_and_merge/blob/HEAD/pm-vit/datasets.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":"298ab77e1ac660f2","mcp_get_code":{"code_sha256":"298ab77e1ac660f2"}},{"arxiv_id":"2503.15234","paper":"/paper/coe-chain-of-explanation-via-automatic-visual","title":"CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification","date":"2025-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YuWLong666/CoE","path":"models/internvl.py","file_url":"https://github.com/YuWLong666/CoE/blob/HEAD/models/internvl.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2503.12769","paper":"/paper/vispeak-visual-instruction-feedback-in","title":"ViSpeak: Visual Instruction Feedback in Streaming Videos","date":"2025-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp-mt/streamingbench","path":"src/model/InternVL.py","file_url":"https://github.com/thunlp-mt/streamingbench/blob/HEAD/src/model/InternVL.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2501.05510","paper":"/paper/ovo-bench-how-far-is-your-video-llms-from","title":"OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?","date":"2025-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JoeLeelyf/OVO-Bench","path":"models/InternVL2.py","file_url":"https://github.com/JoeLeelyf/OVO-Bench/blob/HEAD/models/InternVL2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2412.12693","paper":"/paper/sphere-a-hierarchical-evaluation-on-spatial","title":"SPHERE: A Hierarchical Evaluation on Spatial Perception and Reasoning for Vision-Language Models","date":"2024-12-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zwenyu/SPHERE-VLM","path":"models/vision_language_models/intern_vl2_5.py","file_url":"https://github.com/zwenyu/SPHERE-VLM/blob/HEAD/models/vision_language_models/intern_vl2_5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8e7f5895ff4790f2","mcp_get_code":{"code_sha256":"8e7f5895ff4790f2"}},{"arxiv_id":"2412.09441","paper":"/paper/mos-model-surgery-for-pre-trained-model-based","title":"MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sun-hailong/aaai25-mos","path":"utils/data.py","file_url":"https://github.com/sun-hailong/aaai25-mos/blob/HEAD/utils/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b620954495190c1a","mcp_get_code":{"code_sha256":"b620954495190c1a"}},{"arxiv_id":"2412.06171","paper":"/paper/holmes-vau-towards-long-term-video-anomaly","title":"Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity","date":"2024-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pipixin321/holmesvau","path":"holmesvau/internvl_utils.py","file_url":"https://github.com/pipixin321/holmesvau/blob/HEAD/holmesvau/internvl_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2412.04680","paper":"/paper/superpixel-tokenization-for-vision","title":"Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokens","date":"2024-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jangsoohyuk/SuiT","path":"datasets.py","file_url":"https://github.com/jangsoohyuk/SuiT/blob/HEAD/datasets.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":"ebeb7b6e20a434cf","mcp_get_code":{"code_sha256":"ebeb7b6e20a434cf"}},{"arxiv_id":"2411.19325","paper":"/paper/geobench-vlm-benchmarking-vision-language","title":"GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks","date":"2024-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"the-ai-alliance/geo-bench-vlm","path":"eval_geobenchvlm/internvl_cls_single.py","file_url":"https://github.com/the-ai-alliance/geo-bench-vlm/blob/HEAD/eval_geobenchvlm/internvl_cls_single.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":"3d72a5d533865ae7","mcp_get_code":{"code_sha256":"3d72a5d533865ae7"}},{"arxiv_id":"2411.14429","paper":"/paper/revisiting-the-integration-of-convolution-and","title":"Revisiting the Integration of Convolution and Attention for Vision Backbone","date":"2024-11-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rayleizhu/GLMix","path":"datasets.py","file_url":"https://github.com/rayleizhu/GLMix/blob/HEAD/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2411.11496","paper":"/paper/safe-safe-unsafe-exploring-how-safe-images","title":"Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models","date":"2024-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gzcch/safety_snowball_agent","path":"InternVL_assitant.py","file_url":"https://github.com/gzcch/safety_snowball_agent/blob/HEAD/InternVL_assitant.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2411.03823","paper":"/paper/both-text-and-images-leaked-a-systematic","title":"Both Text and Images Leaked! A Systematic Analysis of Multimodal LLM Data Contamination","date":"2024-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MLLM-Data-Contamination/MM-Detect","path":"mm_detect/mllms/internvl2.py","file_url":"https://github.com/MLLM-Data-Contamination/MM-Detect/blob/HEAD/mm_detect/mllms/internvl2.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":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"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":"lib/datasets.py","file_url":"https://github.com/ssfgunner/SNELL/blob/HEAD/lib/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"77106d449591afd8","mcp_get_code":{"code_sha256":"77106d449591afd8"}},{"arxiv_id":"2410.20444","paper":"/paper/vector-quantization-prompting-for-continual","title":"Vector Quantization Prompting for Continual Learning","date":"2024-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiaolifengmi/VQ-Prompt","path":"dataloaders/utils.py","file_url":"https://github.com/jiaolifengmi/VQ-Prompt/blob/HEAD/dataloaders/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa97aea5d1c8ffb8","mcp_get_code":{"code_sha256":"aa97aea5d1c8ffb8"}},{"arxiv_id":"2410.17885","paper":"/paper/r-cot-reverse-chain-of-thought-problem","title":"R-CoT: Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dle666/r-cot","path":"GeoQA_test/model_vqa_rcot2b.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/GeoQA_test/model_vqa_rcot2b.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2410.17385","paper":"/paper/do-vision-language-models-represent-space-and","title":"Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities","date":"2024-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sled-group/COMFORT","path":"comfort_utils/model_utils/intern_vl.py","file_url":"https://github.com/sled-group/COMFORT/blob/HEAD/comfort_utils/model_utils/intern_vl.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8cf510a10c5f26c3","mcp_get_code":{"code_sha256":"8cf510a10c5f26c3"}},{"arxiv_id":"2410.14179","paper":"/paper/multichartqa-benchmarking-vision-language","title":"MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems","date":"2024-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zivenzhu/multi-chart-qa","path":"code/evaluate_internvl15.py","file_url":"https://github.com/zivenzhu/multi-chart-qa/blob/HEAD/code/evaluate_internvl15.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2410.01733","paper":"/paper/visual-perception-in-text-strings","title":"Visual Perception in Text Strings","date":"2024-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JiaQiSJTU/VisionInText","path":"src/evaluation_mm.py","file_url":"https://github.com/JiaQiSJTU/VisionInText/blob/HEAD/src/evaluation_mm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2409.09808","paper":"/paper/famba-v-fast-vision-mamba-with-cross-layer","title":"Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion","date":"2024-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aiot-mlsys-lab/famba-v","path":"fambav/datasets.py","file_url":"https://github.com/aiot-mlsys-lab/famba-v/blob/HEAD/fambav/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ebeb7b6e20a434cf","mcp_get_code":{"code_sha256":"ebeb7b6e20a434cf"}},{"arxiv_id":"2409.07446","paper":"/paper/adaptive-adapter-routing-for-long-tailed","title":"Adaptive Adapter Routing for Long-Tailed Class-Incremental Learning","date":"2024-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vita-qzh/apart","path":"utils/data.py","file_url":"https://github.com/vita-qzh/apart/blob/HEAD/utils/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b620954495190c1a","mcp_get_code":{"code_sha256":"b620954495190c1a"}},{"arxiv_id":"2408.08693","paper":"/paper/med-pmc-medical-personalized-multi-modal","title":"Med-PMC: Medical Personalized Multi-modal Consultation with a Proactive Ask-First-Observe-Next Paradigm","date":"2024-08-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuhc0428/med-pmc","path":"src/models/InternVL.py","file_url":"https://github.com/liuhc0428/med-pmc/blob/HEAD/src/models/InternVL.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2407.21004","paper":"/paper/evolver-chain-of-evolution-prompting-to-boost","title":"Evolver: Chain-of-Evolution Prompting to Boost Large Multimodal Models for Hateful Meme Detection","date":"2024-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"infaaa/evolver","path":"src/utils.py","file_url":"https://github.com/infaaa/evolver/blob/HEAD/src/utils.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":"f0a261e12d1e7736","mcp_get_code":{"code_sha256":"f0a261e12d1e7736"}},{"arxiv_id":"2407.15240","paper":"/paper/bigbench-a-unified-benchmark-for-social-bias","title":"BIGbench: A Unified Benchmark for Evaluating Multi-dimensional Social Biases in Text-to-Image Models","date":"2024-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigbench2024/bigbench2024","path":"benchmark/internViT_pkg/internvl_detection.py","file_url":"https://github.com/bigbench2024/bigbench2024/blob/HEAD/benchmark/internViT_pkg/internvl_detection.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2407.10918","paper":"/paper/partimagenet-dataset-scaling-up-part-based","title":"PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognition","date":"2024-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LixiaoTHU/PartImageNetPP","path":"eval_multi_dataset.py","file_url":"https://github.com/LixiaoTHU/PartImageNetPP/blob/HEAD/eval_multi_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"123de186a05d2490","mcp_get_code":{"code_sha256":"123de186a05d2490"}},{"arxiv_id":"2407.09087","paper":"/paper/on-the-role-of-discrete-tokenization-in","title":"On the Role of Discrete Tokenization in Visual Representation Learning","date":"2024-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PKU-ML/ClusterMIM","path":"util/datasets.py","file_url":"https://github.com/PKU-ML/ClusterMIM/blob/HEAD/util/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"800cebf161a8aa26","mcp_get_code":{"code_sha256":"800cebf161a8aa26"}},{"arxiv_id":"2407.04903","paper":"/paper/mmsci-a-multimodal-multi-discipline-dataset","title":"MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding","date":"2024-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leezekun/mmsci","path":"mmsci-exps/model_loader.py","file_url":"https://github.com/leezekun/mmsci/blob/HEAD/mmsci-exps/model_loader.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2407.01523","paper":"/paper/mmlongbench-doc-benchmarking-long-context","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","date":"2024-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mayubo2333/mmlongbench-doc","path":"models/internvl_chat.py","file_url":"https://github.com/mayubo2333/mmlongbench-doc/blob/HEAD/models/internvl_chat.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":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2407.00113","paper":"/paper/personalized-federated-continual-learning-via","title":"Personalized Federated Continual Learning via Multi-granularity Prompt","date":"2024-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"skyofbeginning/fedmgp","path":"utils.py","file_url":"https://github.com/skyofbeginning/fedmgp/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a2fe8c39d05e678a","mcp_get_code":{"code_sha256":"a2fe8c39d05e678a"}},{"arxiv_id":"2406.13770","paper":"/paper/elliptical-attention","title":"Elliptical Attention","date":"2024-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stefvk/Elliptical-Attention","path":"ImageNet/datasets.py","file_url":"https://github.com/stefvk/Elliptical-Attention/blob/HEAD/ImageNet/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2406.13762","paper":"/paper/unveiling-the-hidden-structure-of-self","title":"Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis","date":"2024-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rachtsy/KPCA_code","path":"Attack/datasets.py","file_url":"https://github.com/rachtsy/KPCA_code/blob/HEAD/Attack/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2406.11933","paper":"/paper/scaling-efficient-masked-autoencoder-learning","title":"Scaling Efficient Masked Image Modeling on Large Remote Sensing Dataset","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Fengxiang23/SelectiveMAE","path":"SelectiveMAE/util/datasets.py","file_url":"https://github.com/Fengxiang23/SelectiveMAE/blob/HEAD/SelectiveMAE/util/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ae15999500b3952c","mcp_get_code":{"code_sha256":"ae15999500b3952c"}},{"arxiv_id":"2406.11833","paper":"/paper/mmdu-a-multi-turn-multi-image-dialog","title":"MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuziyu77/mmdu","path":"model_generation/InternVL_chat_gen_ans.py","file_url":"https://github.com/liuziyu77/mmdu/blob/HEAD/model_generation/InternVL_chat_gen_ans.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":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2406.11794","paper":"/paper/datacomp-lm-in-search-of-the-next-generation","title":"DataComp-LM: In search of the next generation of training sets for language models","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jieyuz2/taskmeanything","path":"tma/models/qa_model/imageqa_model.py","file_url":"https://github.com/jieyuz2/taskmeanything/blob/HEAD/tma/models/qa_model/imageqa_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f0a261e12d1e7736","mcp_get_code":{"code_sha256":"f0a261e12d1e7736"}},{"arxiv_id":"2406.07537","paper":"/paper/autoregressive-pretraining-with-mamba-in","title":"Autoregressive Pretraining with Mamba in Vision","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oliverrensu/arm","path":"Finetuning/util/datasets.py","file_url":"https://github.com/oliverrensu/arm/blob/HEAD/Finetuning/util/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d24d1a3d833e4faf","mcp_get_code":{"code_sha256":"d24d1a3d833e4faf"}},{"arxiv_id":"2406.07230","paper":"/paper/needle-in-a-multimodal-haystack","title":"Needle In A Multimodal Haystack","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/mm-niah","path":"eval_internvl.py","file_url":"https://github.com/opengvlab/mm-niah/blob/HEAD/eval_internvl.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2406.06462","paper":"/paper/vcr-visual-caption-restoration","title":"VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text","date":"2024-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tianyu-z/vcr","path":"src/evaluation/utils.py","file_url":"https://github.com/tianyu-z/vcr/blob/HEAD/src/evaluation/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC-BY-SA-4.0","inline_ok":false,"code_sha256_prefix":"8e7f5895ff4790f2","mcp_get_code":{"code_sha256":"8e7f5895ff4790f2"}},{"arxiv_id":"2405.15738","paper":"/paper/convllava-hierarchical-backbones-as-visual","title":"ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba/conv-llava","path":"llava/eval/evaluate_grounding.py","file_url":"https://github.com/alibaba/conv-llava/blob/HEAD/llava/eval/evaluate_grounding.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":"b19a532af1216566","mcp_get_code":{"code_sha256":"b19a532af1216566"}},{"arxiv_id":"2405.14156","paper":"/paper/unveiling-the-tapestry-of-consistency-in","title":"Unveiling the Tapestry of Consistency in Large Vision-Language Models","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"foundation-multimodal-models/conbench","path":"eval/InternVL-Chat-V1-5-26B.py","file_url":"https://github.com/foundation-multimodal-models/conbench/blob/HEAD/eval/InternVL-Chat-V1-5-26B.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":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2404.15770","paper":"/paper/chex-interactive-localization-and-region","title":"ChEX: Interactive Localization and Region Description in Chest X-rays","date":"2024-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"philip-mueller/chex","path":"src/dataset/image_transform.py","file_url":"https://github.com/philip-mueller/chex/blob/HEAD/src/dataset/image_transform.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aaa12717b8238a1f","mcp_get_code":{"code_sha256":"aaa12717b8238a1f"}},{"arxiv_id":"2404.15127","paper":"/paper/meddr-diagnosis-guided-bootstrapping-for","title":"GSCo: Towards Generalizable AI in Medicine via Generalist-Specialist Collaboration","date":"2024-04-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sunanhe/meddr","path":"src/dataset/transforms.py","file_url":"https://github.com/sunanhe/meddr/blob/HEAD/src/dataset/transforms.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ddf5cec5e279143","mcp_get_code":{"code_sha256":"3ddf5cec5e279143"}},{"arxiv_id":"2404.15127","paper":"/paper/meddr-diagnosis-guided-bootstrapping-for","title":"GSCo: Towards Generalizable AI in Medicine via Generalist-Specialist Collaboration","date":"2024-04-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sunanhe/meddr","path":"src/train/dataset.py","file_url":"https://github.com/sunanhe/meddr/blob/HEAD/src/train/dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"722750f3bafc8978","mcp_get_code":{"code_sha256":"722750f3bafc8978"}},{"arxiv_id":"2404.14076","paper":"/paper/noise-contrastive-estimation-with-soft","title":"Towards noise contrastive estimation with soft targets for conditional models","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uhlmanngroup/soft-target-infonce","path":"util/data.py","file_url":"https://github.com/uhlmanngroup/soft-target-infonce/blob/HEAD/util/data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8df2b0d7de3b78bb","mcp_get_code":{"code_sha256":"8df2b0d7de3b78bb"}},{"arxiv_id":"2404.12766","paper":"/paper/continual-learning-on-a-diet-learning-from","title":"Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation","date":"2024-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wx-zhang/continual-learning-on-a-diet","path":"dataset/utils.py","file_url":"https://github.com/wx-zhang/continual-learning-on-a-diet/blob/HEAD/dataset/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"35e17b6daeb8ba28","mcp_get_code":{"code_sha256":"35e17b6daeb8ba28"}},{"arxiv_id":"2404.06773","paper":"/paper/adapting-llama-decoder-to-vision-transformer","title":"Adapting LLaMA Decoder to Vision Transformer","date":"2024-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"techmonsterwang/illama","path":"datasets.py","file_url":"https://github.com/techmonsterwang/illama/blob/HEAD/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6a0317bfd6be9557","mcp_get_code":{"code_sha256":"6a0317bfd6be9557"}},{"arxiv_id":"2404.06622","paper":"/paper/calibrating-higher-order-statistics-for-few","title":"Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers","date":"2024-04-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dipamgoswami/fscil-calibration","path":"utils/data.py","file_url":"https://github.com/dipamgoswami/fscil-calibration/blob/HEAD/utils/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b620954495190c1a","mcp_get_code":{"code_sha256":"b620954495190c1a"}},{"arxiv_id":"2404.00974","paper":"/paper/improving-visual-recognition-with","title":"Improving Visual Recognition with Hyperbolical Visual Hierarchy Mapping","date":"2024-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kwonjunn01/Hi-Mapper","path":"datasets.py","file_url":"https://github.com/kwonjunn01/Hi-Mapper/blob/HEAD/datasets.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":"ebeb7b6e20a434cf","mcp_get_code":{"code_sha256":"ebeb7b6e20a434cf"}},{"arxiv_id":"2404.00672","paper":"/paper/a-general-and-efficient-training-for","title":"A General and Efficient Training for Transformer via Token Expansion","date":"2024-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"osilly/tokenexpansion","path":"ToE/EfficientTrain/datasets.py","file_url":"https://github.com/osilly/tokenexpansion/blob/HEAD/ToE/EfficientTrain/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"60fc00ee96a43cdf","mcp_get_code":{"code_sha256":"60fc00ee96a43cdf"}},{"arxiv_id":"2403.18063","paper":"/paper/spectral-convolutional-transformer","title":"Heracles: A Hybrid SSM-Transformer Model for High-Resolution Image and Time-Series Analysis","date":"2024-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"badripatro/heracles","path":"datasets.py","file_url":"https://github.com/badripatro/heracles/blob/HEAD/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bbff8d1aecb5fc69","mcp_get_code":{"code_sha256":"bbff8d1aecb5fc69"}},{"arxiv_id":"2403.17343","paper":"/paper/language-models-are-free-boosters-for","title":"Residual-based Language Models are Free Boosters for Biomedical Imaging","date":"2024-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhixinlai/llmboostmedical","path":"2D_classification/datasets.py","file_url":"https://github.com/zhixinlai/llmboostmedical/blob/HEAD/2D_classification/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2403.16552","paper":"/paper/qkformer-hierarchical-spiking-transformer","title":"QKFormer: Hierarchical Spiking Transformer using Q-K Attention","date":"2024-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Fancyssc/Spiking-Transformers","path":"datasets.py","file_url":"https://github.com/Fancyssc/Spiking-Transformers/blob/HEAD/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aeded02f9fc26708","mcp_get_code":{"code_sha256":"aeded02f9fc26708"}},{"arxiv_id":"2403.15952","paper":"/paper/illusionvqa-a-challenging-optical-illusion","title":"IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models","date":"2024-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csebuetnlp/illusionvqa","path":"inference_code/open_source/internvlm_inference.py","file_url":"https://github.com/csebuetnlp/illusionvqa/blob/HEAD/inference_code/open_source/internvlm_inference.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2403.15360","paper":"/paper/simba-simplified-mamba-based-architecture-for","title":"SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series","date":"2024-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"badripatro/simba","path":"classification/datasets.py","file_url":"https://github.com/badripatro/simba/blob/HEAD/classification/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bbff8d1aecb5fc69","mcp_get_code":{"code_sha256":"bbff8d1aecb5fc69"}},{"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":"lib/datasets.py","file_url":"https://github.com/thu-mig/pyra/blob/HEAD/lib/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4352f21759f08de9","mcp_get_code":{"code_sha256":"4352f21759f08de9"}},{"arxiv_id":"2403.01590","paper":"/paper/the-hidden-attention-of-mamba-models","title":"The Hidden Attention of Mamba Models","date":"2024-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ameenali/hiddenmambaattn","path":"vim/datasets.py","file_url":"https://github.com/ameenali/hiddenmambaattn/blob/HEAD/vim/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ebeb7b6e20a434cf","mcp_get_code":{"code_sha256":"ebeb7b6e20a434cf"}},{"arxiv_id":"2404.03663","paper":"/paper/spike-driven-transformer-v2-meta-spiking","title":"Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"biclab/spike-driven-transformer-v2","path":"classification/util/datasets.py","file_url":"https://github.com/biclab/spike-driven-transformer-v2/blob/HEAD/classification/util/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"800cebf161a8aa26","mcp_get_code":{"code_sha256":"800cebf161a8aa26"}},{"arxiv_id":"2402.11458","paper":"/paper/key-patch-proposer-key-patches-contain-rich","title":"Key Patch Proposer: Key Patches Contain Rich Information","date":"2024-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CA-TT-AC/key-patch-proposer","path":"util/datasets.py","file_url":"https://github.com/CA-TT-AC/key-patch-proposer/blob/HEAD/util/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"800cebf161a8aa26","mcp_get_code":{"code_sha256":"800cebf161a8aa26"}},{"arxiv_id":"2402.11303","paper":"/paper/fvit-a-focal-vision-transformer-with-gabor","title":"FViT: A Focal Vision Transformer with Gabor Filter","date":"2024-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nkusyl/fvit","path":"datasets.py","file_url":"https://github.com/nkusyl/fvit/blob/HEAD/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ec05b468041ed6af","mcp_get_code":{"code_sha256":"ec05b468041ed6af"}},{"arxiv_id":"2402.00033","paper":"/paper/lf-vit-reducing-spatial-redundancy-in-vision","title":"LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition","date":"2024-01-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"edgeai1/lf-vit","path":"deit/datasets.py","file_url":"https://github.com/edgeai1/lf-vit/blob/HEAD/deit/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2312.13271","paper":"/paper/repaint123-fast-and-high-quality-one-image-to","title":"Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting","date":"2023-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"junwuzhang19/repaint123","path":"main2.py","file_url":"https://github.com/junwuzhang19/repaint123/blob/HEAD/main2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"2312.00752","paper":"/paper/mamba-linear-time-sequence-modeling-with","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","date":"2023-12-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thearkaprava/ms-temba","path":"vim/datasets.py","file_url":"https://github.com/thearkaprava/ms-temba/blob/HEAD/vim/datasets.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":"ebeb7b6e20a434cf","mcp_get_code":{"code_sha256":"ebeb7b6e20a434cf"}},{"arxiv_id":"2311.05589","paper":"/paper/a-coefficient-makes-svrg-effective","title":"A Coefficient Makes SVRG Effective","date":"2023-11-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"davidyyd/alpha-SVRG","path":"datasets.py","file_url":"https://github.com/davidyyd/alpha-SVRG/blob/HEAD/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9d57c9f8a153d267","mcp_get_code":{"code_sha256":"9d57c9f8a153d267"}},{"arxiv_id":"2310.15171","paper":"/paper/robodepth-robust-out-of-distribution-depth-1","title":"RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"noahzn/Lite-Mono","path":"lite-mono-pretrain-code/datasets.py","file_url":"https://github.com/noahzn/Lite-Mono/blob/HEAD/lite-mono-pretrain-code/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7c0862f80f8c2ba7","mcp_get_code":{"code_sha256":"7c0862f80f8c2ba7"}},{"arxiv_id":"2310.13593","paper":"/paper/longer-range-contextualized-masked","title":"Learning with Unmasked Tokens Drives Stronger Vision Learners","date":"2023-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver-ai/lut","path":"util/datasets.py","file_url":"https://github.com/naver-ai/lut/blob/HEAD/util/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"800cebf161a8aa26","mcp_get_code":{"code_sha256":"800cebf161a8aa26"}},{"arxiv_id":"2310.12973","paper":"/paper/frozen-transformers-in-language-models-are","title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziqipang/lm4visualencoding","path":"image_classification/datasets.py","file_url":"https://github.com/ziqipang/lm4visualencoding/blob/HEAD/image_classification/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2310.01812","paper":"/paper/ppt-token-pruning-and-pooling-for-efficient","title":"PPT: Token Pruning and Pooling for Efficient Vision Transformers","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xjwu1024/PPT","path":"datasets.py","file_url":"https://github.com/xjwu1024/PPT/blob/HEAD/datasets.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":"ebeb7b6e20a434cf","mcp_get_code":{"code_sha256":"ebeb7b6e20a434cf"}},{"arxiv_id":"2309.15812","paper":"/paper/convolutional-networks-with-oriented-1d-1","title":"Convolutional Networks with Oriented 1D Kernels","date":"2023-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-vl/oriented1d","path":"datasets.py","file_url":"https://github.com/princeton-vl/oriented1d/blob/HEAD/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6a0317bfd6be9557","mcp_get_code":{"code_sha256":"6a0317bfd6be9557"}},{"arxiv_id":"2309.10667","paper":"/paper/learning-tri-modal-embeddings-for-zero-shot","title":"Learning Tri-modal Embeddings for Zero-Shot Soundscape Mapping","date":"2023-09-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mvrl/geoclap","path":"geoclap/utilities/SATMAE_transform.py","file_url":"https://github.com/mvrl/geoclap/blob/HEAD/geoclap/utilities/SATMAE_transform.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"38f07e336b29c0a5","mcp_get_code":{"code_sha256":"38f07e336b29c0a5"}},{"arxiv_id":"2309.03576","paper":"/paper/droppos-pre-training-vision-transformers-by-1","title":"DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions","date":"2023-09-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Haochen-Wang409/DropPos","path":"util/datasets.py","file_url":"https://github.com/Haochen-Wang409/DropPos/blob/HEAD/util/datasets.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":"b1528b5a179ebd3f","mcp_get_code":{"code_sha256":"b1528b5a179ebd3f"}},{"arxiv_id":"2309.02995","paper":"/paper/continual-evidential-deep-learning-for-out-of","title":"Continual Evidential Deep Learning for Out-of-Distribution Detection","date":"2023-09-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eaaguilart/cedl","path":"utils.py","file_url":"https://github.com/eaaguilart/cedl/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b4d4190f298ddc4e","mcp_get_code":{"code_sha256":"b4d4190f298ddc4e"}},{"arxiv_id":"2308.03374","paper":"/paper/heterogeneous-forgetting-compensation-for","title":"Heterogeneous Forgetting Compensation for Class-Incremental Learning","date":"2023-08-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JiahuaDong/HFC","path":"dataset.py","file_url":"https://github.com/JiahuaDong/HFC/blob/HEAD/dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cfae7624aaadda21","mcp_get_code":{"code_sha256":"cfae7624aaadda21"}},{"arxiv_id":"2307.09361","paper":"/paper/moca-self-supervised-representation-learning","title":"MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments","date":"2023-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"valeoai/moca","path":"eval_finetune.py","file_url":"https://github.com/valeoai/moca/blob/HEAD/eval_finetune.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ae21f98447467f18","mcp_get_code":{"code_sha256":"ae21f98447467f18"}},{"arxiv_id":"2307.02251","paper":"/paper/ranpac-random-projections-and-pre-trained","title":"RanPAC: Random Projections and Pre-trained Models for Continual Learning","date":"2023-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ranpac/ranpac","path":"utils/data.py","file_url":"https://github.com/ranpac/ranpac/blob/HEAD/utils/data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8425222b4660e321","mcp_get_code":{"code_sha256":"8425222b4660e321"}},{"arxiv_id":"2307.00395","paper":"/paper/mobilevig-graph-based-sparse-attention-for","title":"MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications","date":"2023-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sldgroup/mobilevig","path":"util/datasets.py","file_url":"https://github.com/sldgroup/mobilevig/blob/HEAD/util/datasets.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":"0fbc07d6adfcd855","mcp_get_code":{"code_sha256":"0fbc07d6adfcd855"}},{"arxiv_id":"2306.06446","paper":"/paper/shiftaddvit-mixture-of-multiplication-1","title":"ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer","date":"2023-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GATECH-EIC/ShiftAddViT","path":"pvt/datasets.py","file_url":"https://github.com/GATECH-EIC/ShiftAddViT/blob/HEAD/pvt/datasets.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":"b1ff741b34908d33","mcp_get_code":{"code_sha256":"b1ff741b34908d33"}},{"arxiv_id":"2304.14636","paper":"/paper/prenas-preferred-one-shot-learning-towards","title":"PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search","date":null,"month_inferred_from_arxiv_id":"2023-04","title_source":"archive","repo":"tinyvision/PreNAS","path":"lib/datasets.py","file_url":"https://github.com/tinyvision/PreNAS/blob/HEAD/lib/datasets.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":"97eb30cd8a8f60a9","mcp_get_code":{"code_sha256":"97eb30cd8a8f60a9"}},{"arxiv_id":"2304.10716","paper":"/paper/joint-token-pruning-and-squeezing-towards","title":"Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers","date":"2023-04-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"megvii-research/TPS-CVPR2023","path":"torch_codebase/datasets.py","file_url":"https://github.com/megvii-research/TPS-CVPR2023/blob/HEAD/torch_codebase/datasets.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":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2304.03284","paper":"/paper/seggpt-segmenting-everything-in-context","title":"SegGPT: Segmenting Everything In Context","date":"2023-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baaivision/painter","path":"Painter/util/datasets.py","file_url":"https://github.com/baaivision/painter/blob/HEAD/Painter/util/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"800cebf161a8aa26","mcp_get_code":{"code_sha256":"800cebf161a8aa26"}},{"arxiv_id":"2304.02330","paper":"/paper/smpconv-self-moving-point-representations-for","title":"SMPConv: Self-moving Point Representations for Continuous Convolution","date":"2023-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sangnekim/SMPConv","path":"smp_imagenet/datasets.py","file_url":"https://github.com/sangnekim/SMPConv/blob/HEAD/smp_imagenet/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6a0317bfd6be9557","mcp_get_code":{"code_sha256":"6a0317bfd6be9557"}},{"arxiv_id":"2303.07598","paper":"/paper/adpe-adversarial-positional-embeddings-for","title":"AdPE: Adversarial Positional Embeddings for Pretraining Vision Transformers via MAE+","date":"2023-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maple-research-lab/AdPE","path":"data_processing/build_dataset.py","file_url":"https://github.com/maple-research-lab/AdPE/blob/HEAD/data_processing/build_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"800cebf161a8aa26","mcp_get_code":{"code_sha256":"800cebf161a8aa26"}},{"arxiv_id":"2302.09462","paper":"/paper/medvit-a-robust-vision-transformer-for","title":"MedViT: A Robust Vision Transformer for Generalized Medical Image Classification","date":"2023-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Omid-Nejati/MedViT","path":"CustomDataset/datasets.py","file_url":"https://github.com/Omid-Nejati/MedViT/blob/HEAD/CustomDataset/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2302.06586","paper":"/paper/stitchable-neural-networks","title":"Stitchable Neural Networks","date":"2023-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziplab/SN-Net","path":"stitching_deit/datasets.py","file_url":"https://github.com/ziplab/SN-Net/blob/HEAD/stitching_deit/datasets.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":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2302.06052","paper":"/paper/cfnet-cascade-fusion-network-for-dense","title":"CEDNet: A Cascade Encoder-Decoder Network for Dense Prediction","date":"2023-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhanggang001/cfnet","path":"datasets.py","file_url":"https://github.com/zhanggang001/cfnet/blob/HEAD/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"6a0317bfd6be9557","mcp_get_code":{"code_sha256":"6a0317bfd6be9557"}},{"arxiv_id":"2301.03831","paper":"/paper/dynamic-grained-encoder-for-vision-1","title":"Dynamic Grained Encoder for Vision Transformers","date":"2023-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stevengrove/vtpack","path":"vtpack/engine/datasets.py","file_url":"https://github.com/stevengrove/vtpack/blob/HEAD/vtpack/engine/datasets.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":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2212.13563","paper":"/paper/noise-aware-learning-from-web-crawled-image","title":"Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning","date":"2022-12-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kakaobrain/noc","path":"noc/dataset/transforms.py","file_url":"https://github.com/kakaobrain/noc/blob/HEAD/noc/dataset/transforms.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"907a99c74d56b0bd","mcp_get_code":{"code_sha256":"907a99c74d56b0bd"}},{"arxiv_id":"2212.05677","paper":"/paper/masked-autoencoders-is-an-effective-solution","title":"Masked autoencoders are effective solution to transformer data-hungry","date":"2022-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"talented-q/sdmae","path":"util/datasets.py","file_url":"https://github.com/talented-q/sdmae/blob/HEAD/util/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"800cebf161a8aa26","mcp_get_code":{"code_sha256":"800cebf161a8aa26"}},{"arxiv_id":"2212.04129","paper":"/paper/deep-model-assembling","title":"Deep Incubation: Training Large Models by Divide-and-Conquering","date":"2022-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leaplabthu/model-assembling","path":"datasets.py","file_url":"https://github.com/leaplabthu/model-assembling/blob/HEAD/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2212.00776","paper":"/paper/resformer-scaling-vits-with-multi-resolution","title":"ResFormer: Scaling ViTs with Multi-Resolution Training","date":"2022-12-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruitian12/resformer","path":"image_classification/datasets.py","file_url":"https://github.com/ruitian12/resformer/blob/HEAD/image_classification/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0b4de2aa27a5231b","mcp_get_code":{"code_sha256":"0b4de2aa27a5231b"}},{"arxiv_id":"2211.12933","paper":"/paper/join-the-high-accuracy-club-on-imagenet-with","title":"Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticket","date":"2022-11-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hpi-xnor/bnext","path":"utils/utils.py","file_url":"https://github.com/hpi-xnor/bnext/blob/HEAD/utils/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":"fdd04ae393554ffa","mcp_get_code":{"code_sha256":"fdd04ae393554ffa"}},{"arxiv_id":"2211.05781","paper":"/paper/demystify-transformers-convolutions-in-modern","title":"Demystify Transformers & Convolutions in Modern Image Deep Networks","date":"2022-11-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/stm-evaluation","path":"classification/datasets.py","file_url":"https://github.com/opengvlab/stm-evaluation/blob/HEAD/classification/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6a0317bfd6be9557","mcp_get_code":{"code_sha256":"6a0317bfd6be9557"}},{"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/datasets.py","file_url":"https://github.com/GATECH-EIC/ViTaLiTy/blob/HEAD/src/datasets.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":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"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":"datasets.py","file_url":"https://github.com/arieseirack/dhvt/blob/HEAD/datasets.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":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2210.00788","paper":"/paper/towards-a-unified-view-on-visual-parameter","title":"Towards a Unified View on Visual Parameter-Efficient Transfer Learning","date":"2022-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bruceyo/V-PETL","path":"util/datasets.py","file_url":"https://github.com/bruceyo/V-PETL/blob/HEAD/util/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"800cebf161a8aa26","mcp_get_code":{"code_sha256":"800cebf161a8aa26"}},{"arxiv_id":"2209.09004","paper":"/paper/ecoformer-energy-saving-attention-with-linear","title":"EcoFormer: Energy-Saving Attention with Linear Complexity","date":"2022-09-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziplab/EcoFormer","path":"pvt/datasets.py","file_url":"https://github.com/ziplab/EcoFormer/blob/HEAD/pvt/datasets.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":"b1ff741b34908d33","mcp_get_code":{"code_sha256":"b1ff741b34908d33"}},{"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/eval_cls.py","file_url":"https://github.com/liuxingbin/dbot/blob/HEAD/evaluation/eval_cls.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":"1902796bef81ffd2","mcp_get_code":{"code_sha256":"1902796bef81ffd2"}},{"arxiv_id":"2208.07049","paper":"/paper/self-supervised-vision-transformers-for","title":"Self-Supervised Vision Transformers for Malware Detection","date":"2022-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sachith500/sherlock","path":"regenerate_experiment_results.py","file_url":"https://github.com/sachith500/sherlock/blob/HEAD/regenerate_experiment_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d3af604efbb5026","mcp_get_code":{"code_sha256":"0d3af604efbb5026"}},{"arxiv_id":"2207.09176","paper":"/paper/self-supervision-can-be-a-good-few-shot","title":"Self-Supervision Can Be a Good Few-Shot Learner","date":"2022-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bbbdylan/unisiam","path":"transform/build_transform.py","file_url":"https://github.com/bbbdylan/unisiam/blob/HEAD/transform/build_transform.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"830d602b5d97e75d","mcp_get_code":{"code_sha256":"830d602b5d97e75d"}},{"arxiv_id":"2207.05501","paper":"/paper/next-vit-next-generation-vision-transformer","title":"Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios","date":"2022-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/next-vit","path":"classification/datasets.py","file_url":"https://github.com/bytedance/next-vit/blob/HEAD/classification/datasets.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":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2207.04978","paper":"/paper/wave-vit-unifying-wavelet-and-transformers","title":"Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning","date":"2022-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YehLi/ImageNetModel","path":"classification/datasets.py","file_url":"https://github.com/YehLi/ImageNetModel/blob/HEAD/classification/datasets.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":"bbff8d1aecb5fc69","mcp_get_code":{"code_sha256":"bbff8d1aecb5fc69"}},{"arxiv_id":"2206.10552","paper":"/paper/vicinity-vision-transformer","title":"Vicinity Vision Transformer","date":"2022-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opennlplab/vicinity-vision-transformer","path":"classification/datasets.py","file_url":"https://github.com/opennlplab/vicinity-vision-transformer/blob/HEAD/classification/datasets.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":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2206.08898","paper":"/paper/sima-simple-softmax-free-attention-for-vision","title":"SimA: Simple Softmax-free Attention for Vision Transformers","date":"2022-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucdvision/sima","path":"datasets.py","file_url":"https://github.com/ucdvision/sima/blob/HEAD/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7791ea55637b67a","mcp_get_code":{"code_sha256":"e7791ea55637b67a"}},{"arxiv_id":"2206.07699","paper":"/paper/prefix-language-models-are-unified-modal","title":"Write and Paint: Generative Vision-Language Models are Unified Modal Learners","date":"2022-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shizhediao/davinci","path":"image_finetune.py","file_url":"https://github.com/shizhediao/davinci/blob/HEAD/image_finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"code_sha256_prefix":"719b9682b050e2c1","mcp_get_code":{"code_sha256":"719b9682b050e2c1"}},{"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":"lib/datasets.py","file_url":"https://github.com/ZhangYuanhan-AI/NOAH/blob/HEAD/lib/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4352f21759f08de9","mcp_get_code":{"code_sha256":"4352f21759f08de9"}},{"arxiv_id":"2206.02967","paper":"/paper/masked-unsupervised-self-training-for-zero","title":"Masked Unsupervised Self-training for Label-free Image Classification","date":"2022-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/must","path":"build_dataset.py","file_url":"https://github.com/salesforce/must/blob/HEAD/build_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"e3abc9c2df1aee16","mcp_get_code":{"code_sha256":"e3abc9c2df1aee16"}},{"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":"mx-mark/dmjd","path":"util/datasets.py","file_url":"https://github.com/mx-mark/dmjd/blob/HEAD/util/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"800cebf161a8aa26","mcp_get_code":{"code_sha256":"800cebf161a8aa26"}},{"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":"classification/datasets.py","file_url":"https://github.com/zengwang430521/tcformer/blob/HEAD/classification/datasets.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":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"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":"datasets/cifar_fs_elite.py","file_url":"https://github.com/hushell/pmf_cvpr22/blob/HEAD/datasets/cifar_fs_elite.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":"f0f38cfab1ecddd0","mcp_get_code":{"code_sha256":"f0f38cfab1ecddd0"}},{"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":"eval/eval_finetuning/eval_finetuning.py","file_url":"https://github.com/sail-sg/mugs/blob/HEAD/eval/eval_finetuning/eval_finetuning.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":"2c33c9d3e647cbf1","mcp_get_code":{"code_sha256":"2c33c9d3e647cbf1"}},{"arxiv_id":"2203.07988","paper":"/paper/smoothing-matters-momentum-transformer-for","title":"Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation","date":"2022-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alpc91/transda","path":"core/datasets/build.py","file_url":"https://github.com/alpc91/transda/blob/HEAD/core/datasets/build.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"025b807a1a19d500","mcp_get_code":{"code_sha256":"025b807a1a19d500"}},{"arxiv_id":"2203.06345","paper":"/paper/the-principle-of-diversity-training-stronger","title":"The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy","date":"2022-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/Diverse-ViT","path":"datasets.py","file_url":"https://github.com/VITA-Group/Diverse-ViT/blob/HEAD/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2203.05962","paper":"/paper/anti-oversmoothing-in-deep-vision","title":"Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice","date":"2022-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/ViT-Anti-Oversmoothing","path":"datasets.py","file_url":"https://github.com/VITA-Group/ViT-Anti-Oversmoothing/blob/HEAD/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1c791d67454f3922","mcp_get_code":{"code_sha256":"1c791d67454f3922"}},{"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":"datasets.py","file_url":"https://github.com/youweiliang/evit/blob/HEAD/datasets.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":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2202.06258","paper":"/paper/flowformer-linearizing-transformers-with","title":"Flowformer: Linearizing Transformers with Conservation Flows","date":"2022-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thuml/Flowformer","path":"Flowformer_CV/datasets.py","file_url":"https://github.com/thuml/Flowformer/blob/HEAD/Flowformer_CV/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"984b0cb17eae025e","mcp_get_code":{"code_sha256":"984b0cb17eae025e"}},{"arxiv_id":"2201.07703","paper":"/paper/q-vit-fully-differentiable-quantization-for","title":"Q-ViT: Fully Differentiable Quantization for Vision Transformer","date":"2022-01-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhexinli/Q-ViT-DeiT","path":"datasets.py","file_url":"https://github.com/zhexinli/Q-ViT-DeiT/blob/HEAD/datasets.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":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2112.07658","paper":"/paper/adavit-adaptive-tokens-for-efficient-vision","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","date":"2021-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVlabs/A-ViT","path":"datasets.py","file_url":"https://github.com/NVlabs/A-ViT/blob/HEAD/datasets.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":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2111.11802","paper":"/paper/pruning-self-attentions-into-convolutional","title":"Pruning Self-attentions into Convolutional Layers in Single Path","date":"2021-11-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhuang-group/spvit","path":"SPViT_DeiT/datasets.py","file_url":"https://github.com/zhuang-group/spvit/blob/HEAD/SPViT_DeiT/datasets.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":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2111.11326","paper":"/paper/dytox-transformers-for-continual-learning","title":"DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion","date":"2021-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arthurdouillard/dytox","path":"continual/datasets.py","file_url":"https://github.com/arthurdouillard/dytox/blob/HEAD/continual/datasets.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":"ad865c09bd36571e","mcp_get_code":{"code_sha256":"ad865c09bd36571e"}},{"arxiv_id":"2108.01390","paper":"/paper/evo-vit-slow-fast-token-evolution-for-dynamic","title":"Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer","date":"2021-08-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YifanXu74/Evo-ViT","path":"datasets.py","file_url":"https://github.com/YifanXu74/Evo-ViT/blob/HEAD/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2107.10224","paper":"/paper/cyclemlp-a-mlp-like-architecture-for-dense","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","date":"2021-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ShoufaChen/CycleMLP","path":"datasets.py","file_url":"https://github.com/ShoufaChen/CycleMLP/blob/HEAD/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2106.09681","paper":"/paper/xcit-cross-covariance-image-transformers","title":"XCiT: Cross-Covariance Image Transformers","date":"2021-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/xcit","path":"datasets.py","file_url":"https://github.com/facebookresearch/xcit/blob/HEAD/datasets.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":"e7791ea55637b67a","mcp_get_code":{"code_sha256":"e7791ea55637b67a"}},{"arxiv_id":"2106.01401","paper":"/paper/container-context-aggregation-network","title":"Container: Context Aggregation Network","date":"2021-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/container","path":"datasets.py","file_url":"https://github.com/allenai/container/blob/HEAD/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2106.00515","paper":"/paper/kvt-k-nn-attention-for-boosting-vision","title":"KVT: k-NN Attention for Boosting Vision Transformers","date":"2021-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"damo-cv/kvt","path":"datasets.py","file_url":"https://github.com/damo-cv/kvt/blob/HEAD/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2105.13677","paper":"/paper/rest-an-efficient-transformer-for-visual","title":"ResT: An Efficient Transformer for Visual Recognition","date":"2021-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wofmanaf/ResT","path":"datasets.py","file_url":"https://github.com/wofmanaf/ResT/blob/HEAD/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"6a0317bfd6be9557","mcp_get_code":{"code_sha256":"6a0317bfd6be9557"}},{"arxiv_id":"2105.12723","paper":"/paper/aggregating-nested-transformers","title":"Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding","date":"2021-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"freder-chen/vitp","path":"util/datasets.py","file_url":"https://github.com/freder-chen/vitp/blob/HEAD/util/datasets.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":"b86ebb0fa1909e0d","mcp_get_code":{"code_sha256":"b86ebb0fa1909e0d"}},{"arxiv_id":"2104.13840","paper":"/paper/twins-revisiting-spatial-attention-design-in","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","date":"2021-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Meituan-AutoML/Twins","path":"datasets.py","file_url":"https://github.com/Meituan-AutoML/Twins/blob/HEAD/datasets.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":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"2104.05707","paper":"/paper/localvit-bringing-locality-to-vision","title":"LocalViT: Bringing Locality to Vision Transformers","date":"2021-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ofsoundof/LocalViT","path":"datasets.py","file_url":"https://github.com/ofsoundof/LocalViT/blob/HEAD/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"1910.01108","paper":"/paper/distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","date":"2019-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"reycn/multi-modal-scale","path":"script/3.evaluation.batch.py","file_url":"https://github.com/reycn/multi-modal-scale/blob/HEAD/script/3.evaluation.batch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"1905.02244","paper":"/paper/searching-for-mobilenetv3","title":"Searching for MobileNetV3","date":"2019-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaolai-sqlai/mobilenetv3","path":"datasets.py","file_url":"https://github.com/xiaolai-sqlai/mobilenetv3/blob/HEAD/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"6a0317bfd6be9557","mcp_get_code":{"code_sha256":"6a0317bfd6be9557"}},{"arxiv_id":"ijcai2023_0111","paper":null,"title":"arXiv:ijcai2023_0111","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"xiaolai-sqlai/RaMLP","path":"datasets.py","file_url":"https://github.com/xiaolai-sqlai/RaMLP/blob/HEAD/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6a0317bfd6be9557","mcp_get_code":{"code_sha256":"6a0317bfd6be9557"}},{"arxiv_id":"aaai_28296","paper":null,"title":"arXiv:aaai_28296","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"skyoux/SemAIM","path":"datasets/datasets.py","file_url":"https://github.com/skyoux/SemAIM/blob/HEAD/datasets/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b1528b5a179ebd3f","mcp_get_code":{"code_sha256":"b1528b5a179ebd3f"}},{"arxiv_id":"aaai_28109","paper":null,"title":"arXiv:aaai_28109","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"YanjingLi0202/Bi-ViT","path":"datasets.py","file_url":"https://github.com/YanjingLi0202/Bi-ViT/blob/HEAD/datasets.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":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"aaai_26008","paper":null,"title":"arXiv:aaai_26008","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ZLKong/Tri-Level-ViT","path":"datasets.py","file_url":"https://github.com/ZLKong/Tri-Level-ViT/blob/HEAD/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"aaai_25860","paper":null,"title":"arXiv:aaai_25860","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ChenMnZ/CF-ViT","path":"deit/datasets.py","file_url":"https://github.com/ChenMnZ/CF-ViT/blob/HEAD/deit/datasets.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":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"aaai_25300","paper":null,"title":"arXiv:aaai_25300","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"qiy20/SAIM","path":"util/datasets.py","file_url":"https://github.com/qiy20/SAIM/blob/HEAD/util/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"800cebf161a8aa26","mcp_get_code":{"code_sha256":"800cebf161a8aa26"}},{"arxiv_id":"aaai_20850","paper":null,"title":"arXiv:aaai_20850","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"BIT-DA/EADA","path":"core/datasets/transforms.py","file_url":"https://github.com/BIT-DA/EADA/blob/HEAD/core/datasets/transforms.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dafc481e534328b4","mcp_get_code":{"code_sha256":"dafc481e534328b4"}},{"arxiv_id":"Zhang_Holmes-VAU_Towards_Long-term_Video_Anomaly_Understanding_at_Any_Granularity_CVPR_2025_paper","paper":null,"title":"arXiv:Zhang_Holmes-VAU_Towards_Long-term_Video_Anomaly_Understanding_at_Any_Granularity_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"pipixin321/HolmesVAU","path":"holmesvau/internvl_utils.py","file_url":"https://github.com/pipixin321/HolmesVAU/blob/HEAD/holmesvau/internvl_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"Yu_LaPE_Layer-adaptive_Position_Embedding_for_Vision_Transformers_with_Independent_Layer_ICCV_2023_paper","paper":null,"title":"arXiv:Yu_LaPE_Layer-adaptive_Position_Embedding_for_Vision_Transformers_with_Independent_Layer_ICCV_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Ingrid725/LaPE","path":"datasets.py","file_url":"https://github.com/Ingrid725/LaPE/blob/HEAD/datasets.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":"578cc9f8fe569c14","mcp_get_code":{"code_sha256":"578cc9f8fe569c14"}},{"arxiv_id":"Yang_PVC_Progressive_Visual_Token_Compression_for_Unified_Image_and_Video_CVPR_2025_paper","paper":null,"title":"arXiv:Yang_PVC_Progressive_Visual_Token_Compression_for_Unified_Image_and_Video_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"OpenGVLab/PVC","path":"utils/preprocess.py","file_url":"https://github.com/OpenGVLab/PVC/blob/HEAD/utils/preprocess.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"Wang_Harnessing_Massive_Satellite_Imagery_with_Efficient_Masked_Image_Modeling_ICCV_2025_paper","paper":null,"title":"arXiv:Wang_Harnessing_Massive_Satellite_Imagery_with_Efficient_Masked_Image_Modeling_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"MiliLab/SelectiveMAE","path":"SelectiveMAE/util/datasets.py","file_url":"https://github.com/MiliLab/SelectiveMAE/blob/HEAD/SelectiveMAE/util/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ae15999500b3952c","mcp_get_code":{"code_sha256":"ae15999500b3952c"}},{"arxiv_id":"Ni_Deep_Incubation_Training_Large_Models_by_Divide-and-Conquering_ICCV_2023_paper","paper":null,"title":"arXiv:Ni_Deep_Incubation_Training_Large_Models_by_Divide-and-Conquering_ICCV_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LeapLabTHU/Deep-Incubation","path":"datasets.py","file_url":"https://github.com/LeapLabTHU/Deep-Incubation/blob/HEAD/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"Meng_Closest_Neighbors_are_Harmful_for_Lightweight_Masked_Auto-encoders_CVPR_2025_paper","paper":null,"title":"arXiv:Meng_Closest_Neighbors_are_Harmful_for_Lightweight_Masked_Auto-encoders_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"SeoLabCornell/NoR-MAE","path":"util/datasets.py","file_url":"https://github.com/SeoLabCornell/NoR-MAE/blob/HEAD/util/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"800cebf161a8aa26","mcp_get_code":{"code_sha256":"800cebf161a8aa26"}},{"arxiv_id":"Li_ShiftwiseConv_Small_Convolutional_Kernel_with_Large_Kernel_Effect_CVPR_2025_paper","paper":null,"title":"arXiv:Li_ShiftwiseConv_Small_Convolutional_Kernel_with_Large_Kernel_Effect_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"lidc54/shift-wiseConv","path":"datasets.py","file_url":"https://github.com/lidc54/shift-wiseConv/blob/HEAD/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6a0317bfd6be9557","mcp_get_code":{"code_sha256":"6a0317bfd6be9557"}},{"arxiv_id":"Li_RepQ-ViT_Scale_Reparameterization_for_Post-Training_Quantization_of_Vision_Transformers_ICCV_2023_paper","paper":null,"title":"arXiv:Li_RepQ-ViT_Scale_Reparameterization_for_Post-Training_Quantization_of_Vision_Transformers_ICCV_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zkkli/RepQ-ViT","path":"classification/utils/build_dataset.py","file_url":"https://github.com/zkkli/RepQ-ViT/blob/HEAD/classification/utils/build_dataset.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":"68109f6081b354bc","mcp_get_code":{"code_sha256":"68109f6081b354bc"}},{"arxiv_id":"Guo_Integrating_Visual_Interpretation_and_Linguistic_Reasoning_for_Geometric_Problem_Solving_ICCV_2025_paper","paper":null,"title":"arXiv:Guo_Integrating_Visual_Interpretation_and_Linguistic_Reasoning_for_Geometric_Problem_Solving_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"guozix/DVLR","path":"eval/MathVerse/evaluation/generate_response_geo_text_qwen_2.py","file_url":"https://github.com/guozix/DVLR/blob/HEAD/eval/MathVerse/evaluation/generate_response_geo_text_qwen_2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"Guo_Improving_Robustness_of_Vision_Transformers_by_Reducing_Sensitivity_To_Patch_CVPR_2023_paper","paper":null,"title":"arXiv:Guo_Improving_Robustness_of_Vision_Transformers_by_Reducing_Sensitivity_To_Patch_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"guoyongcs/RSPC","path":"RSPC_RVT/datasets.py","file_url":"https://github.com/guoyongcs/RSPC/blob/HEAD/RSPC_RVT/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6a5202872e049351","mcp_get_code":{"code_sha256":"6a5202872e049351"}},{"arxiv_id":"Fukuda_Adapter_Merging_with_Centroid_Prototype_Mapping_for_Scalable_Class-Incremental_Learning_CVPR_2025_paper","paper":null,"title":"arXiv:Fukuda_Adapter_Merging_with_Centroid_Prototype_Mapping_for_Scalable_Class-Incremental_Learning_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"tf63/ACMap","path":"src/acmap/utils/data.py","file_url":"https://github.com/tf63/ACMap/blob/HEAD/src/acmap/utils/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4c6fc3b966e06357","mcp_get_code":{"code_sha256":"4c6fc3b966e06357"}},{"arxiv_id":"Danish_GEOBench-VLM_Benchmarking_Vision-Language_Models_for_Geospatial_Tasks_ICCV_2025_paper","paper":null,"title":"arXiv:Danish_GEOBench-VLM_Benchmarking_Vision-Language_Models_for_Geospatial_Tasks_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"The-AI-Alliance/GEO-Bench-VLM","path":"eval_geobenchvlm/internvl_cls_single.py","file_url":"https://github.com/The-AI-Alliance/GEO-Bench-VLM/blob/HEAD/eval_geobenchvlm/internvl_cls_single.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":"3d72a5d533865ae7","mcp_get_code":{"code_sha256":"3d72a5d533865ae7"}},{"arxiv_id":"Bergner_Token_Cropr_Faster_ViTs_for_Quite_a_Few_Tasks_CVPR_2025_paper","paper":null,"title":"arXiv:Bergner_Token_Cropr_Faster_ViTs_for_Quite_a_Few_Tasks_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"benbergner/cropr","path":"cls/utils.py","file_url":"https://github.com/benbergner/cropr/blob/HEAD/cls/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eeba8f16fa2d07a1","mcp_get_code":{"code_sha256":"eeba8f16fa2d07a1"}},{"arxiv_id":"2025.acl-long.663","paper":null,"title":"arXiv:2025.acl-long.663","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"BlueZeros/ReflecTool","path":"reflectool/models/InternVLChat.py","file_url":"https://github.com/BlueZeros/ReflecTool/blob/HEAD/reflectool/models/InternVLChat.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":"57e95166ade5f25c","mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"arxiv_id":"136840281","paper":null,"title":"arXiv:136840281","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"damo-cv/KVT","path":"datasets.py","file_url":"https://github.com/damo-cv/KVT/blob/HEAD/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"arxiv_id":"136810051","paper":null,"title":"arXiv:136810051","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"raoyongming/AMixer","path":"datasets.py","file_url":"https://github.com/raoyongming/AMixer/blob/HEAD/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6a0317bfd6be9557","mcp_get_code":{"code_sha256":"6a0317bfd6be9557"}},{"arxiv_id":"136810034","paper":null,"title":"arXiv:136810034","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Sense-X/UniNet","path":"datasets.py","file_url":"https://github.com/Sense-X/UniNet/blob/HEAD/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2216c38a10fe8cbd","mcp_get_code":{"code_sha256":"2216c38a10fe8cbd"}},{"arxiv_id":"136710433","paper":null,"title":"arXiv:136710433","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Sense-X/SiT","path":"datasets.py","file_url":"https://github.com/Sense-X/SiT/blob/HEAD/datasets.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":"3bc74137ab36aa79","mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}}]}