{"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/gather-features","entry":"gather_features","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":78,"n_papers_ran":4,"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":21,"n_samples_ran":4,"n_samples_fingerprinted":2,"n_places":78,"n_places_pointer_only":39,"by_status":{"ran_honours":1,"ran_violates":1,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"unverified":17},"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":"2609.13991","paper":"/paper/arxiv-2609-13991","title":"Mind2Cloud: EEG-to-Point Cloud Generation with Two-Granularity Diffusion Decoding","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"duasoi/Mind2Cloud","path":"eeg_data_process/clip_loss.py","file_url":"https://github.com/duasoi/Mind2Cloud/blob/HEAD/eeg_data_process/clip_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9ce4a1350299a417","mcp_get_code":{"code_sha256":"9ce4a1350299a417"}},{"arxiv_id":"2609.12454","paper":"/paper/arxiv-2609-12454","title":"Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"JuzhengMiao/Spatial-FAD","path":"open_clip_SpatialFAD/loss.py","file_url":"https://github.com/JuzhengMiao/Spatial-FAD/blob/HEAD/open_clip_SpatialFAD/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2605.30107","paper":"/paper/arxiv-2605-30107","title":"Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"LAION-AI/CLAP","path":"src/laion_clap/clap_module/loss.py","file_url":"https://github.com/LAION-AI/CLAP/blob/HEAD/src/laion_clap/clap_module/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"9b31c784540df0d7","mcp_get_code":{"code_sha256":"9b31c784540df0d7"}},{"arxiv_id":"2605.29380","paper":"/paper/arxiv-2605-29380","title":"TRACER: Persistent Regularization for Robust Multimodal Finetuning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"HesamAsad/TRACER","path":"clip/loss.py","file_url":"https://github.com/HesamAsad/TRACER/blob/HEAD/clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2602.22555","paper":"/paper/arxiv-2602-22555","title":"Autoregressive Visual Decoding from EEG Signals","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"ddicee/avde","path":"models/labram.py","file_url":"https://github.com/ddicee/avde/blob/HEAD/models/labram.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"689bf1cf525e2160","mcp_get_code":{"code_sha256":"689bf1cf525e2160"}},{"arxiv_id":"2601.18190","paper":"/paper/arxiv-2601-18190","title":"Multi-Perspective Subimage CLIP with Keyword Guidance for Remote Sensing Image-Text Retrieval","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Lcrucial1f/MPS-CLIP","path":"models/mpsclip.py","file_url":"https://github.com/Lcrucial1f/MPS-CLIP/blob/HEAD/models/mpsclip.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"97ccd29f6f9846bc","mcp_get_code":{"code_sha256":"97ccd29f6f9846bc"}},{"arxiv_id":"2601.16498","paper":"/paper/arxiv-2601-16498","title":"Expert Knowledge-Guided Decision Calibration for Accurate Fine-Grained Tree Species Classification","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"WHU-USI3DV/TreeCLS","path":"models/open_clip/loss.py","file_url":"https://github.com/WHU-USI3DV/TreeCLS/blob/HEAD/models/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2503.20047","paper":"/paper/med3dvlm-an-efficient-vision-language-model","title":"Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis","date":"2025-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mirthai/med3dvlm","path":"src/model/CLIP.py","file_url":"https://github.com/mirthai/med3dvlm/blob/HEAD/src/model/CLIP.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f78bb358bb60eef1","mcp_get_code":{"code_sha256":"f78bb358bb60eef1"}},{"arxiv_id":"2503.06312","paper":"/paper/geolangbind-unifying-earth-observation-with","title":"GeoLangBind: Unifying Earth Observation with Agglomerative Vision-Language Foundation Models","date":"2025-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiong-zhitong/geolb-siglip","path":"open_clip/src/open_clip/loss.py","file_url":"https://github.com/xiong-zhitong/geolb-siglip/blob/HEAD/open_clip/src/open_clip/loss.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":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2412.04653","paper":"/paper/hidden-in-the-noise-two-stage-robust","title":"Hidden in the Noise: Two-Stage Robust Watermarking for Images","date":"2024-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Kasraarabi/Hidden-in-the-Noise","path":"open_clip/loss.py","file_url":"https://github.com/Kasraarabi/Hidden-in-the-Noise/blob/HEAD/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2412.03561","paper":"/paper/flair-vlm-with-fine-grained-language-informed","title":"FLAIR: VLM with Fine-grained Language-informed Image Representations","date":"2024-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"explainableml/flair","path":"src/flair/loss.py","file_url":"https://github.com/explainableml/flair/blob/HEAD/src/flair/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2411.19757","paper":"/paper/dual-risk-minimization-towards-next-level","title":"Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models","date":"2024-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vaynexie/DRM","path":"clip_m/loss.py","file_url":"https://github.com/vaynexie/DRM/blob/HEAD/clip_m/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2411.10086","paper":"/paper/corrclip-reconstructing-correlations-in-clip","title":"CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation","date":"2024-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zdk258/CorrCLIP","path":"CorrCLIPv1/open_clip/loss.py","file_url":"https://github.com/zdk258/CorrCLIP/blob/HEAD/CorrCLIPv1/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2411.05195","paper":"/paper/on-erroneous-agreements-of-clip-image","title":"On Erroneous Agreements of CLIP Image Embeddings","date":"2024-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lst627/CLIP-Embeds","path":"open_clip/src/open_clip/loss.py","file_url":"https://github.com/lst627/CLIP-Embeds/blob/HEAD/open_clip/src/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2411.03862","paper":"/paper/robin-robust-and-invisible-watermarks-for","title":"ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization","date":"2024-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Hannah1102/ROBIN","path":"open_clip/loss.py","file_url":"https://github.com/Hannah1102/ROBIN/blob/HEAD/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2410.18538","paper":"/paper/smite-segment-me-in-time","title":"SMITE: Segment Me In TimE","date":"2024-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alimohammadiamirhossein/smite","path":"src/latent_optimization.py","file_url":"https://github.com/alimohammadiamirhossein/smite/blob/HEAD/src/latent_optimization.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bec020dc9147bb3b","mcp_get_code":{"code_sha256":"bec020dc9147bb3b"}},{"arxiv_id":"2410.18472","paper":"/paper/what-if-the-input-is-expanded-in-ood","title":"What If the Input is Expanded in OOD Detection?","date":"2024-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tmlr-group/CoVer","path":"open_clip/loss.py","file_url":"https://github.com/tmlr-group/CoVer/blob/HEAD/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2410.10034","paper":"/paper/tulip-token-length-upgraded-clip","title":"TULIP: Token-length Upgraded CLIP","date":"2024-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ivonajdenkoska/tulip","path":"open_clip/loss.py","file_url":"https://github.com/ivonajdenkoska/tulip/blob/HEAD/open_clip/loss.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":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2410.05255","paper":"/paper/seppo-semi-policy-preference-optimization-for","title":"SePPO: Semi-Policy Preference Optimization for Diffusion Alignment","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dwanzhang-ai/seppo","path":"utils/open_clip/loss.py","file_url":"https://github.com/dwanzhang-ai/seppo/blob/HEAD/utils/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2410.05210","paper":"/paper/preserving-multi-modal-capabilities-of-pre","title":"Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ytaek-oh/fsc-clip","path":"src/training/losses/loss.py","file_url":"https://github.com/ytaek-oh/fsc-clip/blob/HEAD/src/training/losses/loss.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"b9b5c04cbd9445bc","mcp_get_code":{"code_sha256":"b9b5c04cbd9445bc"}},{"arxiv_id":"2410.03955","paper":"/paper/model-developmental-safety-a-safety-centric","title":"A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety","date":"2024-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ganglii/devsafety","path":"src/train_eval/loss.py","file_url":"https://github.com/ganglii/devsafety/blob/HEAD/src/train_eval/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2410.01768","paper":"/paper/segearth-ov-towards-traning-free-open","title":"SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images","date":"2024-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"likyoo/SegEarth-OV","path":"open_clip/loss.py","file_url":"https://github.com/likyoo/SegEarth-OV/blob/HEAD/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2410.01756","paper":"/paper/imagefolder-autoregressive-image-generation","title":"ImageFolder: Autoregressive Image Generation with Folded Tokens","date":"2024-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lxa9867/imagefolder","path":"tokenizer/tokenizer_image/cliploss.py","file_url":"https://github.com/lxa9867/imagefolder/blob/HEAD/tokenizer/tokenizer_image/cliploss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2409.13079","paper":"/paper/embedding-geometries-of-contrastive-language","title":"Embedding Geometries of Contrastive Language-Image Pre-Training","date":"2024-09-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eify/open_clip","path":"src/open_clip/loss.py","file_url":"https://github.com/eify/open_clip/blob/HEAD/src/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2408.08849","paper":"/paper/ecg-chat-a-large-ecg-language-model-for","title":"ECG-Chat: A Large ECG-Language Model for Cardiac Disease Diagnosis","date":"2024-08-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YubaoZhao/ECG-Chat","path":"open_clip/open_clip/loss.py","file_url":"https://github.com/YubaoZhao/ECG-Chat/blob/HEAD/open_clip/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3d14dccb8dfdb3d","mcp_get_code":{"code_sha256":"e3d14dccb8dfdb3d"}},{"arxiv_id":"2408.04883","paper":"/paper/proxyclip-proxy-attention-improves-clip-for","title":"ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation","date":"2024-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mc-lan/proxyclip","path":"open_clip/loss.py","file_url":"https://github.com/mc-lan/proxyclip/blob/HEAD/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2407.18559","paper":"/paper/vssd-vision-mamba-with-non-casual-state-space","title":"VSSD: Vision Mamba with Non-Causal State Space Duality","date":"2024-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YuHengsss/Trident","path":"open_clip/loss.py","file_url":"https://github.com/YuHengsss/Trident/blob/HEAD/open_clip/loss.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":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2407.06491","paper":"/paper/videoeval-comprehensive-benchmark-suite-for","title":"VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model","date":"2024-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leexinhao/VideoEval","path":"VidTAB_Zeroshot/eva_clip/loss.py","file_url":"https://github.com/leexinhao/VideoEval/blob/HEAD/VidTAB_Zeroshot/eva_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2407.02887","paper":"/paper/explicitly-guided-information-interaction","title":"Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion","date":"2024-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WHU-USI3DV/EGIInet","path":"models/layers/graph_conv.py","file_url":"https://github.com/WHU-USI3DV/EGIInet/blob/HEAD/models/layers/graph_conv.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e6ba453e7cc8da17","mcp_get_code":{"code_sha256":"e6ba453e7cc8da17"}},{"arxiv_id":"2406.17639","paper":"/paper/mitigate-the-gap-investigating-approaches-for","title":"Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIP","date":"2024-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sarahesl/alignclip","path":"align_clip/loss.py","file_url":"https://github.com/sarahesl/alignclip/blob/HEAD/align_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2406.07543","paper":"/paper/vision-model-pre-training-on-interleaved","title":"Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/lcl","path":"src/open_clip/loss.py","file_url":"https://github.com/opengvlab/lcl/blob/HEAD/src/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2406.07476","paper":"/paper/videollama-2-advancing-spatial-temporal","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"damo-nlp-sg/inf-clip","path":"inf_clip/models/loss.py","file_url":"https://github.com/damo-nlp-sg/inf-clip/blob/HEAD/inf_clip/models/loss.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":"9ad02daca617f28b","mcp_get_code":{"code_sha256":"9ad02daca617f28b"}},{"arxiv_id":"2406.06973","paper":"/paper/rwkv-clip-a-robust-vision-language","title":"RWKV-CLIP: A Robust Vision-Language Representation Learner","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepglint/RWKV-CLIP","path":"loss.py","file_url":"https://github.com/deepglint/RWKV-CLIP/blob/HEAD/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2406.05184","paper":"/paper/the-unmet-promise-of-synthetic-training","title":"The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"scottgeng00/unmet-promise","path":"adapt/clip_custom/loss.py","file_url":"https://github.com/scottgeng00/unmet-promise/blob/HEAD/adapt/clip_custom/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2406.04350","paper":"/paper/prompt-guided-precise-audio-editing-with","title":"Prompt-guided Precise Audio Editing with Diffusion Models","date":"2024-05-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoheliu/audioldm","path":"audioldm/clap/open_clip/loss.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/clap/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b31c784540df0d7","mcp_get_code":{"code_sha256":"9b31c784540df0d7"}},{"arxiv_id":"2405.17537","paper":"/paper/bioscan-clip-bridging-vision-and-genomics-for","title":"CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"3dlg-hcvc/bioscan-clip","path":"bioscanclip/model/loss_func.py","file_url":"https://github.com/3dlg-hcvc/bioscan-clip/blob/HEAD/bioscanclip/model/loss_func.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"89968f9743af3ef4","mcp_get_code":{"code_sha256":"89968f9743af3ef4"}},{"arxiv_id":"2405.08815","paper":"/paper/efficient-vision-language-pre-training-by","title":"Efficient Vision-Language Pre-training by Cluster Masking","date":"2024-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zi-hao-wei/efficient-vision-language-pre-training-by-cluster-masking","path":"open_clip/loss.py","file_url":"https://github.com/zi-hao-wei/efficient-vision-language-pre-training-by-cluster-masking/blob/HEAD/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2405.00740","paper":"/paper/modeling-caption-diversity-in-contrastive","title":"Modeling Caption Diversity in Contrastive Vision-Language Pretraining","date":"2024-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/llip","path":"llip/open_clip/loss.py","file_url":"https://github.com/facebookresearch/llip/blob/HEAD/llip/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2404.16022","paper":"/paper/pulid-pure-and-lightning-id-customization-via","title":"PuLID: Pure and Lightning ID Customization via Contrastive Alignment","date":"2024-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tothebeginning/pulid","path":"eva_clip/loss.py","file_url":"https://github.com/tothebeginning/pulid/blob/HEAD/eva_clip/loss.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":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2404.14055","paper":"/paper/ringid-rethinking-tree-ring-watermarking-for","title":"RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identification","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"showlab/ringid","path":"open_clip/loss.py","file_url":"https://github.com/showlab/ringid/blob/HEAD/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2404.13671","paper":"/paper/filo-zero-shot-anomaly-detection-by-fine","title":"FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization","date":"2024-04-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"casia-iva-lab/filo","path":"models/vv_open_clip/loss.py","file_url":"https://github.com/casia-iva-lab/filo/blob/HEAD/models/vv_open_clip/loss.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":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2404.05231","paper":"/paper/promptad-learning-prompts-with-only-normal","title":"PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection","date":"2024-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"funz-0/promptad","path":"PromptAD/CLIPAD/loss.py","file_url":"https://github.com/funz-0/promptad/blob/HEAD/PromptAD/CLIPAD/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Unlicense","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2404.04956","paper":"/paper/gaussian-shading-provable-performance","title":"Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models","date":"2024-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bsmhmmlf/Gaussian-Shading","path":"open_clip/loss.py","file_url":"https://github.com/bsmhmmlf/Gaussian-Shading/blob/HEAD/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2404.02132","paper":"/paper/vitamin-designing-scalable-vision-models-in","title":"ViTamin: Designing Scalable Vision Models in the Vision-Language Era","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"beckschen/vitamin","path":"ViTamin/open_clip/loss.py","file_url":"https://github.com/beckschen/vitamin/blob/HEAD/ViTamin/open_clip/loss.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":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2403.17007","paper":"/paper/dreamlip-language-image-pre-training-with","title":"DreamLIP: Language-Image Pre-training with Long Captions","date":"2024-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zyf0619sjtu/DreamLIP","path":"open_clip/loss.py","file_url":"https://github.com/zyf0619sjtu/DreamLIP/blob/HEAD/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC-BY-4.0","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2403.16831","paper":"/paper/urbanvlp-a-multi-granularity-vision-language","title":"UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction","date":"2024-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"citymind-lab/urbanvlp","path":"open_clip_mine/loss.py","file_url":"https://github.com/citymind-lab/urbanvlp/blob/HEAD/open_clip_mine/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2403.15378","paper":"/paper/long-clip-unlocking-the-long-text-capability","title":"Long-CLIP: Unlocking the Long-Text Capability of CLIP","date":"2024-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"beichenzbc/long-clip","path":"open_clip_long/loss.py","file_url":"https://github.com/beichenzbc/long-clip/blob/HEAD/open_clip_long/loss.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":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2403.10153","paper":"/paper/improving-medical-multi-modal-contrastive","title":"Improving Medical Multi-modal Contrastive Learning with Expert Annotations","date":"2024-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ykumards/eclip","path":"eclip/model/eclip_module.py","file_url":"https://github.com/ykumards/eclip/blob/HEAD/eclip/model/eclip_module.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"4b7fdd1c6930c4d9","mcp_get_code":{"code_sha256":"4b7fdd1c6930c4d9"}},{"arxiv_id":"2403.06495","paper":"/paper/toward-generalist-anomaly-detection-via-in","title":"Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mala-lab/WinCLIP","path":"open_clip/loss.py","file_url":"https://github.com/mala-lab/WinCLIP/blob/HEAD/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2401.02955","paper":"/paper/open-vocabulary-sam-segment-and-recognize","title":"Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively","date":"2024-01-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"harboryuan/ovsam","path":"ext/open_clip/loss.py","file_url":"https://github.com/harboryuan/ovsam/blob/HEAD/ext/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2312.12856","paper":"/paper/skyscript-a-large-and-semantically-diverse","title":"SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing","date":"2023-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangzhecheng/skyscript","path":"src/open_clip/loss.py","file_url":"https://github.com/wangzhecheng/skyscript/blob/HEAD/src/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2312.11038","paper":"/paper/unichest-conquer-and-divide-pre-training-for","title":"UniChest: Conquer-and-Divide Pre-training for Multi-Source Chest X-Ray Classification","date":"2023-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"elfenreigen/unichest","path":"factory/loss.py","file_url":"https://github.com/elfenreigen/unichest/blob/HEAD/factory/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2312.01886","paper":"/paper/instructta-instruction-tuned-targeted-attack","title":"InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xunguangwang/instructta","path":"EVA-CLIP/rei/eva_clip/loss.py","file_url":"https://github.com/xunguangwang/instructta/blob/HEAD/EVA-CLIP/rei/eva_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2311.17048","paper":"/paper/zero-shot-referring-expression-comprehension","title":"Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions","date":"2023-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"show-han/zeroshot_rec","path":"VLA_finetune/open_clip/loss.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/loss.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":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2311.12908","paper":"/paper/diffusion-model-alignment-using-direct","title":"Diffusion Model Alignment Using Direct Preference Optimization","date":"2023-11-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SalesforceAIResearch/DiffusionDPO","path":"utils/open_clip/loss.py","file_url":"https://github.com/SalesforceAIResearch/DiffusionDPO/blob/HEAD/utils/open_clip/loss.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":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2311.01723","paper":"/paper/towards-calibrated-robust-fine-tuning-of","title":"Towards Calibrated Robust Fine-Tuning of Vision-Language Models","date":"2023-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MLAI-Yonsei/CaRot","path":"clip/loss.py","file_url":"https://github.com/MLAI-Yonsei/CaRot/blob/HEAD/clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2311.00566","paper":"/paper/croma-remote-sensing-representations-with-1","title":"CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders","date":"2023-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"antofuller/croma","path":"pretrain_croma.py","file_url":"https://github.com/antofuller/croma/blob/HEAD/pretrain_croma.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"816756cd7d531829","mcp_get_code":{"code_sha256":"816756cd7d531829"}},{"arxiv_id":"2310.18961","paper":"/paper/anomalyclip-object-agnostic-prompt-learning","title":"AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection","date":"2023-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zqhang/WinCLIP-pytorch","path":"src/open_clip/loss.py","file_url":"https://github.com/zqhang/WinCLIP-pytorch/blob/HEAD/src/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2310.01403","paper":"/paper/clipself-vision-transformer-distills-itself","title":"CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wusize/clipself","path":"src/open_clip/loss.py","file_url":"https://github.com/wusize/clipself/blob/HEAD/src/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"fd6321f5fd69ea0a","mcp_get_code":{"code_sha256":"fd6321f5fd69ea0a"}},{"arxiv_id":"2308.15939","paper":"/paper/anovl-adapting-vision-language-models-for","title":"Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization","date":"2023-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hq-deng/AnoVL","path":"open_clip/loss.py","file_url":"https://github.com/hq-deng/AnoVL/blob/HEAD/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2308.13320","paper":"/paper/fine-tuning-can-cripple-your-foundation-model","title":"Fine-tuning can cripple your foundation model; preserving features may be the solution","date":"2023-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"omegafragger/ldifs_code","path":"loss/clip_loss.py","file_url":"https://github.com/omegafragger/ldifs_code/blob/HEAD/loss/clip_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2308.12213","paper":"/paper/clipn-for-zero-shot-ood-detection-teaching","title":"CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No","date":"2023-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xmed-lab/CLIPN","path":"hand-crafted/src/open_clip/loss.py","file_url":"https://github.com/xmed-lab/CLIPN/blob/HEAD/hand-crafted/src/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"61c4ca21dc698a56","mcp_get_code":{"code_sha256":"61c4ca21dc698a56"}},{"arxiv_id":"2308.05734","paper":"/paper/audioldm-2-learning-holistic-audio-generation","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","date":"2023-08-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoheliu/AudioLDM2","path":"audioldm2/clap/open_clip/loss.py","file_url":"https://github.com/haoheliu/AudioLDM2/blob/HEAD/audioldm2/clap/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b31c784540df0d7","mcp_get_code":{"code_sha256":"9b31c784540df0d7"}},{"arxiv_id":"2308.01313","paper":"/paper/more-context-less-distraction-visual","title":"PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts","date":"2023-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umd-huang-lab/perceptionCLIP","path":"clip/loss.py","file_url":"https://github.com/umd-huang-lab/perceptionCLIP/blob/HEAD/clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2307.12732","paper":"/paper/clip-kd-an-empirical-study-of-distilling-clip","title":"CLIP-KD: An Empirical Study of CLIP Model Distillation","date":"2023-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"winycg/clip-kd","path":"src/open_clip/loss.py","file_url":"https://github.com/winycg/clip-kd/blob/HEAD/src/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2306.03065","paper":"/paper/libauc-a-deep-learning-library-for-x-risk","title":"LibAUC: A Deep Learning Library for X-Risk Optimization","date":"2023-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Optimization-AI/LibAUC","path":"libauc/losses/contrastive.py","file_url":"https://github.com/Optimization-AI/LibAUC/blob/HEAD/libauc/losses/contrastive.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0e719e1b1ed02c5a","mcp_get_code":{"code_sha256":"0e719e1b1ed02c5a"}},{"arxiv_id":"2305.17382","paper":"/paper/a-zero-few-shot-anomaly-classification-and","title":"APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD","date":"2023-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bychelsea/vand-april-gan","path":"open_clip/loss.py","file_url":"https://github.com/bychelsea/vand-april-gan/blob/HEAD/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2304.08480","paper":"/paper/disco-clip-a-distributed-contrastive-loss-for","title":"DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training","date":"2023-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlfoundations/open_clip","path":"src/open_clip/loss.py","file_url":"https://github.com/mlfoundations/open_clip/blob/HEAD/src/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e105065a1a8c0e5a","mcp_get_code":{"code_sha256":"e105065a1a8c0e5a"}},{"arxiv_id":"2303.14814","paper":"/paper/winclip-zero-few-shot-anomaly-classification","title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","date":"2023-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"caoyunkang/WinClip","path":"WinCLIP/CLIPAD/loss.py","file_url":"https://github.com/caoyunkang/WinClip/blob/HEAD/WinCLIP/CLIPAD/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2303.07240","paper":"/paper/pmc-clip-contrastive-language-image-pre","title":"PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents","date":"2023-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WeixiongLin/PMC-CLIP","path":"src/pmc_clip/loss/utils.py","file_url":"https://github.com/WeixiongLin/PMC-CLIP/blob/HEAD/src/pmc_clip/loss/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0425170c0cb7b081","mcp_get_code":{"code_sha256":"0425170c0cb7b081"}},{"arxiv_id":"2302.14138","paper":"/paper/layer-grafted-pre-training-bridging","title":"Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations","date":"2023-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/layerGraftedPretraining_ICLR23","path":"utils/pretrain.py","file_url":"https://github.com/VITA-Group/layerGraftedPretraining_ICLR23/blob/HEAD/utils/pretrain.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"0cb11d4906fe4ba1","mcp_get_code":{"code_sha256":"0cb11d4906fe4ba1"}},{"arxiv_id":"2302.14042","paper":"/paper/knowledge-enhanced-pre-training-for-auto","title":"Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images","date":"2023-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaoman-zhang/kad","path":"A3_CLIP/factory/loss.py","file_url":"https://github.com/xiaoman-zhang/kad/blob/HEAD/A3_CLIP/factory/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2302.03668","paper":"/paper/hard-prompts-made-easy-gradient-based-1","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","date":"2023-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YuxinWenRick/hard-prompts-made-easy","path":"open_clip/loss.py","file_url":"https://github.com/YuxinWenRick/hard-prompts-made-easy/blob/HEAD/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2301.07094","paper":"/paper/learning-customized-visual-models-with","title":"Learning Customized Visual Models with Retrieval-Augmented Knowledge","date":"2023-01-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/react","path":"react_customization/src/open_clip/loss.py","file_url":"https://github.com/microsoft/react/blob/HEAD/react_customization/src/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"2212.04501","paper":"/paper/learning-video-representations-from-large","title":"Learning Video Representations from Large Language Models","date":"2022-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/lavila","path":"lavila/models/loss.py","file_url":"https://github.com/facebookresearch/lavila/blob/HEAD/lavila/models/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"19519e7e08dd0087","mcp_get_code":{"code_sha256":"19519e7e08dd0087"}},{"arxiv_id":"2212.00638","paper":"/paper/finetune-like-you-pretrain-improved","title":"Finetune like you pretrain: Improved finetuning of zero-shot vision models","date":"2022-12-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"locuslab/flyp","path":"clip/loss.py","file_url":"https://github.com/locuslab/flyp/blob/HEAD/clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"Ma_ReMP-AD_Retrieval-enhanced_Multi-modal_Prompt_Fusion_for_Few-Shot_Industrial_Visual_Anomaly_ICCV_2025_paper","paper":null,"title":"arXiv:Ma_ReMP-AD_Retrieval-enhanced_Multi-modal_Prompt_Fusion_for_Few-Shot_Industrial_Visual_Anomaly_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"cshcma/ReMP-AD","path":"open_clip/loss.py","file_url":"https://github.com/cshcma/ReMP-AD/blob/HEAD/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"arxiv_id":"Hertz_Style_Aligned_Image_Generation_via_Shared_Attention_CVPR_2024_paper","paper":null,"title":"arXiv:Hertz_Style_Aligned_Image_Generation_via_Shared_Attention_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"aim-uofa/StyleDrop-PyTorch","path":"open_clip/loss.py","file_url":"https://github.com/aim-uofa/StyleDrop-PyTorch/blob/HEAD/open_clip/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddcbd45e940484ee","mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}}]}