{"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/load-state-dict","entry":"load_state_dict","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":114,"n_papers_ran":41,"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":51,"n_samples_ran":17,"n_samples_fingerprinted":0,"n_places":114,"n_places_pointer_only":43,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":6,"ran_fixture":0,"ran":11,"unverified":34},"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":"2606.20559","paper":"/paper/arxiv-2606-20559","title":"UNIEGO: Proxies as Mediators for Unified Egocentric Video Representation Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Wenhao-Chi/UNIEGO","path":"timesformer/models/helpers.py","file_url":"https://github.com/Wenhao-Chi/UNIEGO/blob/HEAD/timesformer/models/helpers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"83ec90904c246b55","mcp_get_code":{"code_sha256":"83ec90904c246b55"}},{"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/factory.py","file_url":"https://github.com/LAION-AI/CLAP/blob/HEAD/src/laion_clap/clap_module/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"70e141a0d42038bd","mcp_get_code":{"code_sha256":"70e141a0d42038bd"}},{"arxiv_id":"2603.25047","paper":"/paper/arxiv-2603-25047","title":"The Order Is The Message","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"JordanRL/OrderedLearning","path":"analysis_tools/data_loader.py","file_url":"https://github.com/JordanRL/OrderedLearning/blob/HEAD/analysis_tools/data_loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d89c3d327ee96ce0","mcp_get_code":{"code_sha256":"d89c3d327ee96ce0"}},{"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/factory.py","file_url":"https://github.com/WHU-USI3DV/TreeCLS/blob/HEAD/models/open_clip/factory.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ef8f5bfd8696abff","mcp_get_code":{"code_sha256":"ef8f5bfd8696abff"}},{"arxiv_id":"2505.06068","paper":"/paper/noise-consistent-siamese-diffusion-for","title":"Noise-Consistent Siamese-Diffusion for Medical Image Synthesis and Segmentation","date":"2025-05-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qiukunpeng/siamese-diffusion","path":"cldm/model.py","file_url":"https://github.com/qiukunpeng/siamese-diffusion/blob/HEAD/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8ba1107b08c79b8f","mcp_get_code":{"code_sha256":"8ba1107b08c79b8f"}},{"arxiv_id":"2504.14151","paper":"/paper/locate-3d-real-world-object-localization-via","title":"Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D","date":"2025-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/locate-3d","path":"models/locate_3d.py","file_url":"https://github.com/facebookresearch/locate-3d/blob/HEAD/models/locate_3d.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"bf69a371a23b5cf6","mcp_get_code":{"code_sha256":"bf69a371a23b5cf6"}},{"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/factory.py","file_url":"https://github.com/xiong-zhitong/geolb-siglip/blob/HEAD/open_clip/src/open_clip/factory.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":"ef8f5bfd8696abff","mcp_get_code":{"code_sha256":"ef8f5bfd8696abff"}},{"arxiv_id":"2501.01790","paper":"/paper/ingredients-blending-custom-photos-with-video","title":"Ingredients: Blending Custom Photos with Video Diffusion Transformers","date":"2025-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"feizc/ingredients","path":"models/eva_clip/factory.py","file_url":"https://github.com/feizc/ingredients/blob/HEAD/models/eva_clip/factory.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":"ab854bdad372c33e","mcp_get_code":{"code_sha256":"ab854bdad372c33e"}},{"arxiv_id":"2412.10569","paper":"/paper/learning-to-merge-tokens-via-decoupled","title":"Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers","date":"2024-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huggingface/pytorch-image-models","path":"timm/models/_helpers.py","file_url":"https://github.com/huggingface/pytorch-image-models/blob/HEAD/timm/models/_helpers.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":"7fdbe56543eec6df","mcp_get_code":{"code_sha256":"7fdbe56543eec6df"}},{"arxiv_id":"2411.15245","paper":"/paper/anytext2-visual-text-generation-and-editing","title":"AnyText2: Visual Text Generation and Editing With Customizable Attributes","date":"2024-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tyxsspa/anytext2","path":"cldm/model.py","file_url":"https://github.com/tyxsspa/anytext2/blob/HEAD/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2411.06959","paper":"/paper/enat-rethinking-spatial-temporal-interactions","title":"ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis","date":"2024-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leaplabthu/enat","path":"taming/models/modeling_utils.py","file_url":"https://github.com/leaplabthu/enat/blob/HEAD/taming/models/modeling_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"934f2eb98d647821","mcp_get_code":{"code_sha256":"934f2eb98d647821"}},{"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/factory.py","file_url":"https://github.com/lst627/CLIP-Embeds/blob/HEAD/open_clip/src/open_clip/factory.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ef8f5bfd8696abff","mcp_get_code":{"code_sha256":"ef8f5bfd8696abff"}},{"arxiv_id":"2410.21638","paper":"/paper/adapting-diffusion-models-for-improved-prompt","title":"Adapting Diffusion Models for Improved Prompt Compliance and Controllable Image Synthesis","date":"2024-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DeepakSridhar/fgdm","path":"controlnet/cldm/model.py","file_url":"https://github.com/DeepakSridhar/fgdm/blob/HEAD/controlnet/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2410.19079","paper":"/paper/bifrost-3d-aware-image-compositing-with","title":"BIFRÖST: 3D-Aware Image compositing with Language Instructions","date":"2024-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lingxiao-li/Bifrost","path":"Main_Bifrost/cldm/model.py","file_url":"https://github.com/lingxiao-li/Bifrost/blob/HEAD/Main_Bifrost/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2410.17534","paper":"/paper/ovt-b-a-new-large-scale-benchmark-for-open","title":"OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Coo1Sea/OVT-B-Dataset","path":"diffusers_clean/modeling_utils.py","file_url":"https://github.com/Coo1Sea/OVT-B-Dataset/blob/HEAD/diffusers_clean/modeling_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":"fa98be725f1850b4","mcp_get_code":{"code_sha256":"fa98be725f1850b4"}},{"arxiv_id":"2410.13136","paper":"/paper/unlocking-the-capabilities-of-masked","title":"Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiwanhur/unlockmgm","path":"muse/modeling_utils.py","file_url":"https://github.com/jiwanhur/unlockmgm/blob/HEAD/muse/modeling_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"934f2eb98d647821","mcp_get_code":{"code_sha256":"934f2eb98d647821"}},{"arxiv_id":"2410.04372","paper":"/paper/diffusionfake-enhancing-generalization-in","title":"DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion","date":"2024-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"skJack/DiffusionFake","path":"cldm/model.py","file_url":"https://github.com/skJack/DiffusionFake/blob/HEAD/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2410.00320","paper":"/paper/pointad-comprehending-3d-anomalies-from","title":"PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection","date":"2024-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zqhang/PointAD","path":"AnomalyCLIP_lib/model_load.py","file_url":"https://github.com/zqhang/PointAD/blob/HEAD/AnomalyCLIP_lib/model_load.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"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/factory.py","file_url":"https://github.com/eify/open_clip/blob/HEAD/src/open_clip/factory.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ef8f5bfd8696abff","mcp_get_code":{"code_sha256":"ef8f5bfd8696abff"}},{"arxiv_id":"2409.12346","paper":"/paper/simultaneous-music-separation-and-generation","title":"Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models","date":null,"month_inferred_from_arxiv_id":"2024-09","title_source":"archive","repo":"karchkha/msg-ld","path":"src/clap/clap_module/factory.py","file_url":"https://github.com/karchkha/msg-ld/blob/HEAD/src/clap/clap_module/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"af72484d5cfd7097","mcp_get_code":{"code_sha256":"af72484d5cfd7097"}},{"arxiv_id":"2409.08260","paper":"/paper/improving-text-guided-object-inpainting-with","title":"Improving Text-guided Object Inpainting with Semantic Pre-inpainting","date":"2024-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nnn-s/catdiffusion","path":"mldm/model.py","file_url":"https://github.com/nnn-s/catdiffusion/blob/HEAD/mldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2409.01055","paper":"/paper/follow-your-canvas-higher-resolution-video","title":"Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation","date":"2024-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mayuelala/followyourcanvas","path":"diffusers/modeling_utils.py","file_url":"https://github.com/mayuelala/followyourcanvas/blob/HEAD/diffusers/modeling_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8e334e23cc90f5e3","mcp_get_code":{"code_sha256":"8e334e23cc90f5e3"}},{"arxiv_id":"2408.16450","paper":"/paper/what-to-preserve-and-what-to-transfer","title":"What to Preserve and What to Transfer: Faithful, Identity-Preserving Diffusion-based Hairstyle Transfer","date":"2024-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cychungg/hairfusion","path":"cldm/model.py","file_url":"https://github.com/cychungg/hairfusion/blob/HEAD/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"35ad646f5b9e8cbf","mcp_get_code":{"code_sha256":"35ad646f5b9e8cbf"}},{"arxiv_id":"2407.06250","paper":"/paper/fairdiff-fair-segmentation-with-point-image","title":"FairDiff: Fair Segmentation with Point-Image Diffusion","date":"2024-07-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wenyi-li/fairdiff","path":"MaskImageGen/cldm/model.py","file_url":"https://github.com/wenyi-li/fairdiff/blob/HEAD/MaskImageGen/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2407.03179","paper":"/paper/motion-meets-attention-video-motion-prompts","title":"Motion meets Attention: Video Motion Prompts","date":"2024-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"q1xiangchen/vmps","path":"timesformer/models/helpers.py","file_url":"https://github.com/q1xiangchen/vmps/blob/HEAD/timesformer/models/helpers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"83ec90904c246b55","mcp_get_code":{"code_sha256":"83ec90904c246b55"}},{"arxiv_id":"2406.18958","paper":"/paper/anycontrol-create-your-artwork-with-versatile","title":"AnyControl: Create Your Artwork with Versatile Control on Text-to-Image Generation","date":"2024-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"open-mmlab/anycontrol","path":"models/util.py","file_url":"https://github.com/open-mmlab/anycontrol/blob/HEAD/models/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"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/factory.py","file_url":"https://github.com/sarahesl/alignclip/blob/HEAD/align_clip/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"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/factory.py","file_url":"https://github.com/opengvlab/lcl/blob/HEAD/src/open_clip/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0b94bc3f6eb369a4","mcp_get_code":{"code_sha256":"0b94bc3f6eb369a4"}},{"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/factory.py","file_url":"https://github.com/damo-nlp-sg/inf-clip/blob/HEAD/inf_clip/factory.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":"0b94bc3f6eb369a4","mcp_get_code":{"code_sha256":"0b94bc3f6eb369a4"}},{"arxiv_id":"2406.05478","paper":"/paper/revisiting-non-autoregressive-transformers","title":"Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis","date":"2024-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leaplabthu/improvednat","path":"taming/models/modeling_utils.py","file_url":"https://github.com/leaplabthu/improvednat/blob/HEAD/taming/models/modeling_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"934f2eb98d647821","mcp_get_code":{"code_sha256":"934f2eb98d647821"}},{"arxiv_id":"2406.05205","paper":"/paper/cplip-zero-shot-learning-for-histopathology","title":"CPLIP: Zero-Shot Learning for Histopathology with Comprehensive Vision-Language Alignment","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iyyakuttiiyappan/CPLIP","path":"models/factory.py","file_url":"https://github.com/iyyakuttiiyappan/CPLIP/blob/HEAD/models/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"arxiv_id":"2406.04312","paper":"/paper/reno-enhancing-one-step-text-to-image-models","title":"ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/DOODL","path":"my_half_diffusers/modeling_utils.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/my_half_diffusers/modeling_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":"77bd5e6e8ca8c91d","mcp_get_code":{"code_sha256":"77bd5e6e8ca8c91d"}},{"arxiv_id":"2406.02485","paper":"/paper/stable-pose-leveraging-transformers-for-pose","title":"Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation","date":"2024-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ai-med/stablepose","path":"cldm/utils.py","file_url":"https://github.com/ai-med/stablepose/blob/HEAD/cldm/utils.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":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2406.00816","paper":"/paper/invisible-backdoor-attacks-on-diffusion","title":"Invisible Backdoor Attacks on Diffusion Models","date":"2024-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"invisibletriggerdiffusion/invisible_triggers_for_diffusion","path":"diffusers/modeling_utils.py","file_url":"https://github.com/invisibletriggerdiffusion/invisible_triggers_for_diffusion/blob/HEAD/diffusers/modeling_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"77bd5e6e8ca8c91d","mcp_get_code":{"code_sha256":"77bd5e6e8ca8c91d"}},{"arxiv_id":"2405.18503","paper":"/paper/soundctm-uniting-score-based-and-consistency","title":"SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation","date":"2024-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sony/soundctm","path":"clap/clap_module/factory.py","file_url":"https://github.com/sony/soundctm/blob/HEAD/clap/clap_module/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6ce126db645cc0a7","mcp_get_code":{"code_sha256":"6ce126db645cc0a7"}},{"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/factory.py","file_url":"https://github.com/facebookresearch/llip/blob/HEAD/llip/open_clip/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"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/factory.py","file_url":"https://github.com/casia-iva-lab/filo/blob/HEAD/models/vv_open_clip/factory.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":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"arxiv_id":"2404.11474","paper":"/paper/towards-highly-realistic-artistic-style","title":"Towards Highly Realistic Artistic Style Transfer via Stable Diffusion with Step-aware and Layer-aware Prompt","date":"2024-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jamie-cheung/lsast","path":"cldm/model.py","file_url":"https://github.com/jamie-cheung/lsast/blob/HEAD/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"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/factory.py","file_url":"https://github.com/funz-0/promptad/blob/HEAD/PromptAD/CLIPAD/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Unlicense","inline_ok":true,"code_sha256_prefix":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"arxiv_id":"2404.03635","paper":"/paper/wordepth-variational-language-prior-for","title":"WorDepth: Variational Language Prior for Monocular Depth Estimation","date":"2024-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Adonis-galaxy/WorDepth","path":"src/networks/wordepth.py","file_url":"https://github.com/Adonis-galaxy/WorDepth/blob/HEAD/src/networks/wordepth.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b9bb350524a8fa9f","mcp_get_code":{"code_sha256":"b9bb350524a8fa9f"}},{"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/factory.py","file_url":"https://github.com/beckschen/vitamin/blob/HEAD/ViTamin/open_clip/factory.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":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"arxiv_id":"2404.01740","paper":"/paper/weakly-supervised-audio-separation-via-bi","title":"Weakly-supervised Audio Separation via Bi-modal Semantic Similarity","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/BiModalAudioSeparation","path":"models/laion_clap/clap_module/factory.py","file_url":"https://github.com/microsoft/BiModalAudioSeparation/blob/HEAD/models/laion_clap/clap_module/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"af72484d5cfd7097","mcp_get_code":{"code_sha256":"af72484d5cfd7097"}},{"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/factory.py","file_url":"https://github.com/beichenzbc/long-clip/blob/HEAD/open_clip_long/factory.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":"0b94bc3f6eb369a4","mcp_get_code":{"code_sha256":"0b94bc3f6eb369a4"}},{"arxiv_id":"2403.12570","paper":"/paper/adapting-visual-language-models-for","title":"Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images","date":"2024-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mediabrain-sjtu/mvfa-ad","path":"CLIP/clip.py","file_url":"https://github.com/mediabrain-sjtu/mvfa-ad/blob/HEAD/CLIP/clip.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"arxiv_id":"2403.11614","paper":"/paper/crs-diff-controllable-generative-remote","title":"CRS-Diff: Controllable Remote Sensing Image Generation with Diffusion Model","date":"2024-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Sonettoo/CRS-Diff","path":"models/util.py","file_url":"https://github.com/Sonettoo/CRS-Diff/blob/HEAD/models/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2403.08268","paper":"/paper/follow-your-click-open-domain-regional-image","title":"Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts","date":"2024-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mayuelala/followyourclick","path":"diffusers/modeling_utils.py","file_url":"https://github.com/mayuelala/followyourclick/blob/HEAD/diffusers/modeling_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b57cacefe65c27ce","mcp_get_code":{"code_sha256":"b57cacefe65c27ce"}},{"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/factory.py","file_url":"https://github.com/mala-lab/WinCLIP/blob/HEAD/open_clip/factory.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":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"arxiv_id":"2402.11846","paper":"/paper/unlearncanvas-a-stylized-image-dataset-to","title":"UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Con6924/SPM","path":"src/models/merge_spm.py","file_url":"https://github.com/Con6924/SPM/blob/HEAD/src/models/merge_spm.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":"b8e710925cbb4290","mcp_get_code":{"code_sha256":"b8e710925cbb4290"}},{"arxiv_id":"2402.10259","paper":"/paper/gaussianobject-just-taking-four-images-to-get","title":"GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GaussianObject/GaussianObject","path":"cldm/model.py","file_url":"https://github.com/GaussianObject/GaussianObject/blob/HEAD/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2401.10032","paper":"/paper/fregrad-lightweight-and-fast-frequency-aware","title":"FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocoder","date":"2024-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaistmm/fregrad","path":"inference.py","file_url":"https://github.com/kaistmm/fregrad/blob/HEAD/inference.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ffe1eb32d5d78e7e","mcp_get_code":{"code_sha256":"ffe1eb32d5d78e7e"}},{"arxiv_id":"2401.09048","paper":"/paper/compose-and-conquer-diffusion-based-3d-depth","title":"Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis","date":"2024-01-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tomtom1103/compose-and-conquer","path":"models/util.py","file_url":"https://github.com/tomtom1103/compose-and-conquer/blob/HEAD/models/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2401.08815","paper":"/paper/adversarial-supervision-makes-layout-to-image","title":"Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive","date":"2024-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"boschresearch/aldm","path":"cldm/model.py","file_url":"https://github.com/boschresearch/aldm/blob/HEAD/cldm/model.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":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2312.15736","paper":"/paper/towards-real-world-blind-face-restoration-1","title":"Towards Real-World Blind Face Restoration with Generative Diffusion Prior","date":"2023-12-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chenxx89/bfrffusion","path":"models/models.py","file_url":"https://github.com/chenxx89/bfrffusion/blob/HEAD/models/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87337881055f7a57","mcp_get_code":{"code_sha256":"87337881055f7a57"}},{"arxiv_id":"2312.14091","paper":"/paper/hd-painter-high-resolution-and-prompt","title":"HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models","date":"2023-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"picsart-ai-research/hd-painter","path":"src/models/common.py","file_url":"https://github.com/picsart-ai-research/hd-painter/blob/HEAD/src/models/common.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a8e36ab156c631d","mcp_get_code":{"code_sha256":"0a8e36ab156c631d"}},{"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/factory.py","file_url":"https://github.com/wangzhecheng/skyscript/blob/HEAD/src/open_clip/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"arxiv_id":"2312.11376","paper":"/paper/clim-contrastive-language-image-mosaic-for","title":"CLIM: Contrastive Language-Image Mosaic for Region Representation","date":"2023-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wusize/clim","path":"src/open_clip/factory.py","file_url":"https://github.com/wusize/clim/blob/HEAD/src/open_clip/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"arxiv_id":"2312.06607","paper":"/paper/diad-a-diffusion-based-framework-for-multi","title":"DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection","date":"2023-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lewandofskee/DiAD","path":"finetune_autoencoder.py","file_url":"https://github.com/lewandofskee/DiAD/blob/HEAD/finetune_autoencoder.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":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2312.02139","paper":"/paper/diffit-diffusion-vision-transformers-for","title":"DiffiT: Diffusion Vision Transformers for Image Generation","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nvlabs/diffit","path":"diffit/dist_util.py","file_url":"https://github.com/nvlabs/diffit/blob/HEAD/diffit/dist_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"bd2d797cf36610b5","mcp_get_code":{"code_sha256":"bd2d797cf36610b5"}},{"arxiv_id":"2312.01725","paper":"/paper/stableviton-learning-semantic-correspondence","title":"StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rlawjdghek/stableviton","path":"cldm/model.py","file_url":"https://github.com/rlawjdghek/stableviton/blob/HEAD/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"35ad646f5b9e8cbf","mcp_get_code":{"code_sha256":"35ad646f5b9e8cbf"}},{"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/factory.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/factory.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":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"arxiv_id":"2311.17005","paper":"/paper/mvbench-a-comprehensive-multi-modal-video","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","date":"2023-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/ask-anything","path":"video_chat/models/eva_vit.py","file_url":"https://github.com/opengvlab/ask-anything/blob/HEAD/video_chat/models/eva_vit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0ba0ac7553b4501c","mcp_get_code":{"code_sha256":"0ba0ac7553b4501c"}},{"arxiv_id":"2311.09084","paper":"/paper/contrastive-transformer-learning-with","title":"Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hcplab-sysu/personsearch-ctlg","path":"models/vit.py","file_url":"https://github.com/hcplab-sysu/personsearch-ctlg/blob/HEAD/models/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1b59d3b93db06ff9","mcp_get_code":{"code_sha256":"1b59d3b93db06ff9"}},{"arxiv_id":"2311.04442","paper":"/paper/ss-mae-spatial-spectral-masked-auto-encoder","title":"SS-MAE: Spatial-Spectral Masked Auto-Encoder for Multi-Source Remote Sensing Image Classification","date":"2023-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"summitgao/ss-mae","path":"net/VIT/layers/helpers.py","file_url":"https://github.com/summitgao/ss-mae/blob/HEAD/net/VIT/layers/helpers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6dc13e8f8b2c3d96","mcp_get_code":{"code_sha256":"6dc13e8f8b2c3d96"}},{"arxiv_id":"2311.03054","paper":"/paper/anytext-multilingual-visual-text-generation","title":"AnyText: Multilingual Visual Text Generation And Editing","date":"2023-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tyxsspa/anytext","path":"cldm/model.py","file_url":"https://github.com/tyxsspa/anytext/blob/HEAD/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"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/AnomalyCLIP","path":"AnomalyCLIP_lib/model_load.py","file_url":"https://github.com/zqhang/AnomalyCLIP/blob/HEAD/AnomalyCLIP_lib/model_load.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"arxiv_id":"2310.13165","paper":"/paper/cyclenet-rethinking-cycle-consistency-in-text-1","title":"CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sled-group/cyclenet","path":"cycleNet/model.py","file_url":"https://github.com/sled-group/cyclenet/blob/HEAD/cycleNet/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7e221c57761ea4ce","mcp_get_code":{"code_sha256":"7e221c57761ea4ce"}},{"arxiv_id":"2310.04415","paper":"/paper/why-do-we-need-weight-decay-in-modern-deep","title":"Why Do We Need Weight Decay in Modern Deep Learning?","date":"2023-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tml-epfl/why-weight-decay","path":"large_language_models/model.py","file_url":"https://github.com/tml-epfl/why-weight-decay/blob/HEAD/large_language_models/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"a3534f10e80ca748","mcp_get_code":{"code_sha256":"a3534f10e80ca748"}},{"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/factory.py","file_url":"https://github.com/wusize/clipself/blob/HEAD/src/open_clip/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"arxiv_id":"2308.14686","paper":"/paper/360-degree-panorama-generation-from-few","title":"360-Degree Panorama Generation from Few Unregistered NFoV Images","date":"2023-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shanemankiw/panodiff","path":"cldm/model.py","file_url":"https://github.com/shanemankiw/panodiff/blob/HEAD/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"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":"src/open_clip/factory.py","file_url":"https://github.com/xmed-lab/clipn/blob/HEAD/src/open_clip/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5e42380894ae9205","mcp_get_code":{"code_sha256":"5e42380894ae9205"}},{"arxiv_id":"2308.09592","paper":"/paper/stablevideo-text-driven-consistency-aware","title":"StableVideo: Text-driven Consistency-aware Diffusion Video Editing","date":"2023-08-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rese1f/stablevideo","path":"cldm/model.py","file_url":"https://github.com/rese1f/stablevideo/blob/HEAD/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2308.01546","paper":"/paper/musicldm-enhancing-novelty-in-text-to-music","title":"MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies","date":"2023-08-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"retrocirce/musicldm","path":"interface/src/clap/clap_module/factory.py","file_url":"https://github.com/retrocirce/musicldm/blob/HEAD/interface/src/clap/clap_module/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"af72484d5cfd7097","mcp_get_code":{"code_sha256":"af72484d5cfd7097"}},{"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/factory.py","file_url":"https://github.com/winycg/clip-kd/blob/HEAD/src/open_clip/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"arxiv_id":"2307.12560","paper":"/paper/interpolating-between-images-with-diffusion","title":"Interpolating between Images with Diffusion Models","date":"2023-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clintonjwang/controlnet","path":"cldm/model.py","file_url":"https://github.com/clintonjwang/controlnet/blob/HEAD/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2307.10829","paper":"/paper/exact-diffusion-inversion-via-bi-directional","title":"Exact Diffusion Inversion via Bi-directional Integration Approximation","date":"2023-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guoqiang-zhang-x/BDIA","path":"image-editing/my_diffusers/modeling_utils.py","file_url":"https://github.com/guoqiang-zhang-x/BDIA/blob/HEAD/image-editing/my_diffusers/modeling_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"77bd5e6e8ca8c91d","mcp_get_code":{"code_sha256":"77bd5e6e8ca8c91d"}},{"arxiv_id":"2306.17253","paper":"/paper/towards-zero-shot-scale-aware-monocular-depth","title":"Towards Zero-Shot Scale-Aware Monocular Depth Estimation","date":"2023-06-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cake-lab/Mobile-AR-Depth-Estimation","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"98303a9870582d70","mcp_get_code":{"code_sha256":"98303a9870582d70"}},{"arxiv_id":"2306.11134","paper":"/paper/openp5-benchmarking-foundation-models-for","title":"OpenP5: An Open-Source Platform for Developing, Training, and Evaluating LLM-based Recommender Systems","date":"2023-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jeykigung/P5","path":"src/utils.py","file_url":"https://github.com/jeykigung/P5/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5a21ebce306df07c","mcp_get_code":{"code_sha256":"5a21ebce306df07c"}},{"arxiv_id":"2306.07280","paper":"/paper/controlling-text-to-image-diffusion-by","title":"Controlling Text-to-Image Diffusion by Orthogonal Finetuning","date":"2023-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zeju1997/oft","path":"oft-control/oldm/model.py","file_url":"https://github.com/zeju1997/oft/blob/HEAD/oft-control/oldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2306.05720","paper":"/paper/beyond-surface-statistics-scene","title":"Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model","date":"2023-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yc015/scene-representation-diffusion-model","path":"modified_diffusers/modeling_utils.py","file_url":"https://github.com/yc015/scene-representation-diffusion-model/blob/HEAD/modified_diffusers/modeling_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"77bd5e6e8ca8c91d","mcp_get_code":{"code_sha256":"77bd5e6e8ca8c91d"}},{"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/factory.py","file_url":"https://github.com/bychelsea/vand-april-gan/blob/HEAD/open_clip/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"arxiv_id":"2305.16322","paper":"/paper/uni-controlnet-all-in-one-control-to-text-to-1","title":"Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models","date":"2023-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shihaozhaozsh/uni-controlnet","path":"models/util.py","file_url":"https://github.com/shihaozhaozsh/uni-controlnet/blob/HEAD/models/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2305.14302","paper":"/paper/vip5-towards-multimodal-foundation-models-for","title":"VIP5: Towards Multimodal Foundation Models for Recommendation","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jeykigung/vip5","path":"src/utils.py","file_url":"https://github.com/jeykigung/vip5/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5a21ebce306df07c","mcp_get_code":{"code_sha256":"5a21ebce306df07c"}},{"arxiv_id":"2305.11147","paper":"/paper/unicontrol-a-unified-diffusion-model-for-1","title":"UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild","date":"2023-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/unicontrol","path":"cldm/model.py","file_url":"https://github.com/salesforce/unicontrol/blob/HEAD/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2305.02034","paper":"/paper/samrs-scaling-up-remote-sensing-segmentation","title":"SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model","date":"2023-05-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wenquanlu/handrefiner","path":"cldm/model.py","file_url":"https://github.com/wenquanlu/handrefiner/blob/HEAD/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2304.05568","paper":"/paper/improving-diffusion-models-for-scene-text","title":"Improving Diffusion Models for Scene Text Editing with Dual Encoders","date":"2023-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucsb-nlp-chang/diffste","path":"diffusers/modeling_utils.py","file_url":"https://github.com/ucsb-nlp-chang/diffste/blob/HEAD/diffusers/modeling_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"77bd5e6e8ca8c91d","mcp_get_code":{"code_sha256":"77bd5e6e8ca8c91d"}},{"arxiv_id":"2304.04269","paper":"/paper/humansd-a-native-skeleton-guided-diffusion","title":"HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation","date":"2023-04-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiangchenyin/grpose","path":"cldm/utils.py","file_url":"https://github.com/xiangchenyin/grpose/blob/HEAD/cldm/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":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"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/factory.py","file_url":"https://github.com/caoyunkang/WinClip/blob/HEAD/WinCLIP/CLIPAD/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"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/factory.py","file_url":"https://github.com/WeixiongLin/PMC-CLIP/blob/HEAD/src/pmc_clip/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"arxiv_id":"2301.12900","paper":"/paper/depgraph-towards-any-structural-pruning","title":"DepGraph: Towards Any Structural Pruning","date":"2023-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VainF/Torch-Pruning","path":"torch_pruning/serialization.py","file_url":"https://github.com/VainF/Torch-Pruning/blob/HEAD/torch_pruning/serialization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"44927cfc49a45803","mcp_get_code":{"code_sha256":"44927cfc49a45803"}},{"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/factory.py","file_url":"https://github.com/microsoft/react/blob/HEAD/react_customization/src/open_clip/factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b3a4d17e1df3140","mcp_get_code":{"code_sha256":"4b3a4d17e1df3140"}},{"arxiv_id":"2212.11684","paper":"/paper/scene-aware-egocentric-3d-human-pose","title":"Scene-aware Egocentric 3D Human Pose Estimation","date":"2022-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jianwang-mpi/SceneEgo","path":"network/pose_resnet.py","file_url":"https://github.com/jianwang-mpi/SceneEgo/blob/HEAD/network/pose_resnet.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bb7cf362aae536cb","mcp_get_code":{"code_sha256":"bb7cf362aae536cb"}},{"arxiv_id":"2211.07636","paper":"/paper/eva-exploring-the-limits-of-masked-visual","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","date":"2022-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baaivision/eva","path":"EVA-01/clip/eva_clip.py","file_url":"https://github.com/baaivision/eva/blob/HEAD/EVA-01/clip/eva_clip.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cad32ae74b9cae67","mcp_get_code":{"code_sha256":"cad32ae74b9cae67"}},{"arxiv_id":"2210.04135","paper":"/paper/volta-vision-language-transformer-with-weakly","title":"VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment","date":"2022-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ShramanPramanick/VoLTA","path":"Pre-training/swin_helpers.py","file_url":"https://github.com/ShramanPramanick/VoLTA/blob/HEAD/Pre-training/swin_helpers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc3a13e8155e8140","mcp_get_code":{"code_sha256":"bc3a13e8155e8140"}},{"arxiv_id":"2208.12306","paper":"/paper/multimedia-generative-script-learning-for","title":"Multimedia Generative Script Learning for Task Planning","date":"2022-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EagleW/Multimedia-Generative-Script-Learning-for-Task-Planning","path":"utils_.py","file_url":"https://github.com/EagleW/Multimedia-Generative-Script-Learning-for-Task-Planning/blob/HEAD/utils_.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5a21ebce306df07c","mcp_get_code":{"code_sha256":"5a21ebce306df07c"}},{"arxiv_id":"2208.11284","paper":"/paper/at-ddpm-restoring-faces-degraded-by","title":"AT-DDPM: Restoring Faces degraded by Atmospheric Turbulence using Denoising Diffusion Probabilistic Models","date":"2022-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nithin-gk/at-ddpm","path":"guided_diffusion/dist_util.py","file_url":"https://github.com/nithin-gk/at-ddpm/blob/HEAD/guided_diffusion/dist_util.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":"f3da2d61d9c48642","mcp_get_code":{"code_sha256":"f3da2d61d9c48642"}},{"arxiv_id":"2208.01313","paper":"/paper/unified-normalization-for-accelerating-and","title":"Unified Normalization for Accelerating and Stabilizing Transformers","date":"2022-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hikvision-research/unified-normalization","path":"image_classification/utils.py","file_url":"https://github.com/hikvision-research/unified-normalization/blob/HEAD/image_classification/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":"73f773e3a43253f7","mcp_get_code":{"code_sha256":"73f773e3a43253f7"}},{"arxiv_id":"2206.03452","paper":"/paper/can-cnns-be-more-robust-than-transformers","title":"Can CNNs Be More Robust Than Transformers?","date":"2022-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucsc-vlaa/robustcnn","path":"timm/models/helpers.py","file_url":"https://github.com/ucsc-vlaa/robustcnn/blob/HEAD/timm/models/helpers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a5729ac034a0df02","mcp_get_code":{"code_sha256":"a5729ac034a0df02"}},{"arxiv_id":"2203.14509","paper":"/paper/automated-progressive-learning-for-efficient","title":"Automated Progressive Learning for Efficient Training of Vision Transformers","date":"2022-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"changlin31/autoprog","path":"prog/helpers.py","file_url":"https://github.com/changlin31/autoprog/blob/HEAD/prog/helpers.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":"6725eb03753f6554","mcp_get_code":{"code_sha256":"6725eb03753f6554"}},{"arxiv_id":"2203.10233","paper":"/paper/direcformer-a-directed-attention-in","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","date":"2022-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uark-cviu/direcformer","path":"slowfast/models/helpers.py","file_url":"https://github.com/uark-cviu/direcformer/blob/HEAD/slowfast/models/helpers.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":"83ec90904c246b55","mcp_get_code":{"code_sha256":"83ec90904c246b55"}},{"arxiv_id":"2201.12083","paper":"/paper/dynamixer-a-vision-mlp-architecture-with","title":"DynaMixer: A Vision MLP Architecture with Dynamic Mixing","date":"2022-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziyuwwang/dynamixer","path":"models/utils.py","file_url":"https://github.com/ziyuwwang/dynamixer/blob/HEAD/models/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"11fcdc72cbeefc1a","mcp_get_code":{"code_sha256":"11fcdc72cbeefc1a"}},{"arxiv_id":"2110.07641","paper":"/paper/non-deep-networks-1","title":"Non-deep Networks","date":"2021-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"imankgoyal/NonDeepNetworks","path":"imagenet/timm/models/helpers.py","file_url":"https://github.com/imankgoyal/NonDeepNetworks/blob/HEAD/imagenet/timm/models/helpers.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":"bc3a13e8155e8140","mcp_get_code":{"code_sha256":"bc3a13e8155e8140"}},{"arxiv_id":"2106.12368","paper":"/paper/vision-permutator-a-permutable-mlp-like","title":"Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition","date":"2021-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"houqb/visionpermutator","path":"utils.py","file_url":"https://github.com/houqb/visionpermutator/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"66fb30c5dcdc3404","mcp_get_code":{"code_sha256":"66fb30c5dcdc3404"}},{"arxiv_id":"2002.01685","paper":"/paper/parsing-as-pretraining","title":"Parsing as Pretraining","date":"2020-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huggingface/pytorch-pretrained-BERT","path":"src/transformers/models/visual_bert/convert_visual_bert_original_pytorch_checkpoint_to_pytorch.py","file_url":"https://github.com/huggingface/pytorch-pretrained-BERT/blob/HEAD/src/transformers/models/visual_bert/convert_visual_bert_original_pytorch_checkpoint_to_pytorch.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":"766143fdc27ade86","mcp_get_code":{"code_sha256":"766143fdc27ade86"}},{"arxiv_id":"1905.02249","paper":"/paper/mixmatch-a-holistic-approach-to-semi","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","date":"2019-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"viig99/mixmatch-freesound","path":"kaggle_submission.py","file_url":"https://github.com/viig99/mixmatch-freesound/blob/HEAD/kaggle_submission.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"197f711034e07fc3","mcp_get_code":{"code_sha256":"197f711034e07fc3"}},{"arxiv_id":"1903.00875","paper":"/paper/meta-sr-a-magnification-arbitrary-network-for","title":"Meta-SR: A Magnification-Arbitrary Network for Super-Resolution","date":"2019-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Lornatang/Meta_RDN-PyTorch","path":"utils.py","file_url":"https://github.com/Lornatang/Meta_RDN-PyTorch/blob/HEAD/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":"a23bcbc6ca2999f0","mcp_get_code":{"code_sha256":"a23bcbc6ca2999f0"}},{"arxiv_id":"1809.00219","paper":"/paper/esrgan-enhanced-super-resolution-generative","title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","date":"2018-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Lornatang/ESRGAN-PyTorch","path":"utils.py","file_url":"https://github.com/Lornatang/ESRGAN-PyTorch/blob/HEAD/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":"08e3b22c15672b97","mcp_get_code":{"code_sha256":"08e3b22c15672b97"}},{"arxiv_id":"1804.02767","paper":"/paper/yolov3-an-incremental-improvement","title":"YOLOv3: An Incremental Improvement","date":"2018-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Lornatang/PyTorch-yolov3","path":"yolov3_pytorch/models/utils.py","file_url":"https://github.com/Lornatang/PyTorch-yolov3/blob/HEAD/yolov3_pytorch/models/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":"4c4f887dd3b9d98b","mcp_get_code":{"code_sha256":"4c4f887dd3b9d98b"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"enhuiz/torchnmt","path":"torchnmt/networks/transformer.py","file_url":"https://github.com/enhuiz/torchnmt/blob/HEAD/torchnmt/networks/transformer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"adfc2d27068e936c","mcp_get_code":{"code_sha256":"adfc2d27068e936c"}},{"arxiv_id":"1609.04802","paper":"/paper/photo-realistic-single-image-super-resolution","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","date":"2016-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Lornatang/SRGAN-PyTorch","path":"utils.py","file_url":"https://github.com/Lornatang/SRGAN-PyTorch/blob/HEAD/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":"08e3b22c15672b97","mcp_get_code":{"code_sha256":"08e3b22c15672b97"}},{"arxiv_id":"1411.1784","paper":"/paper/conditional-generative-adversarial-nets","title":"Conditional Generative Adversarial Nets","date":"2014-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Lornatang/CGAN-PyTorch","path":"conditional_gan/utils/checkpoint.py","file_url":"https://github.com/Lornatang/CGAN-PyTorch/blob/HEAD/conditional_gan/utils/checkpoint.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":"9f036873455dfa2c","mcp_get_code":{"code_sha256":"9f036873455dfa2c"}},{"arxiv_id":"1409.5185","paper":"/paper/deeply-supervised-nets","title":"Deeply-Supervised Nets","date":"2014-09-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ellisdg/3DUnetCNN","path":"unet3d/models/build.py","file_url":"https://github.com/ellisdg/3DUnetCNN/blob/HEAD/unet3d/models/build.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fb1d0885dc8670c6","mcp_get_code":{"code_sha256":"fb1d0885dc8670c6"}},{"arxiv_id":"Cao_LeftRefill_Filling_Right_Canvas_based_on_Left_Reference_through_Generalized_CVPR_2024_paper","paper":null,"title":"arXiv:Cao_LeftRefill_Filling_Right_Canvas_based_on_Left_Reference_through_Generalized_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ewrfcas/LeftRefill","path":"inpainting_ldm/model.py","file_url":"https://github.com/ewrfcas/LeftRefill/blob/HEAD/inpainting_ldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2025.findings-emnlp.1385","paper":null,"title":"arXiv:2025.findings-emnlp.1385","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"bowen-upenn/ControlText","path":"cldm/model.py","file_url":"https://github.com/bowen-upenn/ControlText/blob/HEAD/cldm/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"df733a879693145d","mcp_get_code":{"code_sha256":"df733a879693145d"}},{"arxiv_id":"2023.findings-emnlp.644","paper":null,"title":"arXiv:2023.findings-emnlp.644","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"jeykigung/VIP5","path":"src/utils.py","file_url":"https://github.com/jeykigung/VIP5/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5a21ebce306df07c","mcp_get_code":{"code_sha256":"5a21ebce306df07c"}}]}