{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/clip/papers/ran/2","list_of":"/method/clip","method":"CLIP","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not isolate this method inside it.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":2,"pages_in_order":7,"rows_per_page":100,"rows":[101,200],"of":649,"counts":{"archive_papers_tagged":3094,"with_a_code_link":1617,"where_syntology_ran_a_sample":649,"not_listed_spam_title":0,"listed":3094,"listed_where_code_ran":649,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":554,"every_run_a_failure_of_syntologys_instrument":95,"listed_with_a_run_with_no_instrument_failure":554,"listed_every_run_a_failure_of_syntologys_instrument":95,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/clip/papers/ran/1","prev":"/method/clip/papers/ran/1","next":"/method/clip/papers/ran/3","papers":[{"paper":"/paper/segearth-ov-towards-traning-free-open","slug":"segearth-ov-towards-traning-free-open","title":"SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images","date":"2024-10-02","arxiv_id":"2410.01768","n_code_links":2,"syntology":{"ran":6,"of":9,"n_ran_checked":4,"n_instrument":2,"unverified":3,"pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["likyoo/SegEarth-OV"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/pointad-comprehending-3d-anomalies-from","slug":"pointad-comprehending-3d-anomalies-from","title":"PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection","date":"2024-10-01","arxiv_id":"2410.00320","n_code_links":1,"syntology":{"ran":17,"of":26,"n_ran_checked":11,"n_instrument":6,"unverified":9,"pointer_only":23,"phrase":"17 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 9 unverified","official":{"repos":["zqhang/pointad"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":2,"n_ran_no_instrument_failure":11,"n_unverified":8,"ran_from_kinds":["community","official"]}}},{"paper":"/paper/magnet-we-never-know-how-text-to-image","slug":"magnet-we-never-know-how-text-to-image","title":"Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function","date":"2024-09-30","arxiv_id":"2409.19967","n_code_links":1,"syntology":{"ran":11,"of":17,"n_ran_checked":10,"n_instrument":1,"unverified":6,"pointer_only":17,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["i2-multimedia-lab/magnet"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/federated-learning-from-vision-language","slug":"federated-learning-from-vision-language","title":"Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method","date":"2024-09-29","arxiv_id":"2409.19610","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":3,"n_instrument":4,"unverified":3,"pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["PanBikang/PromptFolio"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/clip-moe-towards-building-mixture-of-experts","slug":"clip-moe-towards-building-mixture-of-experts","title":"CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling","date":"2024-09-28","arxiv_id":"2409.19291","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["OpenSparseLLMs/CLIP-MoE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/emu3-next-token-prediction-is-all-you-need","slug":"emu3-next-token-prediction-is-all-you-need","title":"Emu3: Next-Token Prediction is All You Need","date":"2024-09-27","arxiv_id":"2409.18869","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":3,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/the-hard-positive-truth-about-vision-language","slug":"the-hard-positive-truth-about-vision-language","title":"The Hard Positive Truth about Vision-Language Compositionality","date":"2024-09-26","arxiv_id":"2409.17958","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["amitakamath/hard_positives"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/multiclimate-multimodal-stance-detection-on","slug":"multiclimate-multimodal-stance-detection-on","title":"MultiClimate: Multimodal Stance Detection on Climate Change Videos","date":"2024-09-26","arxiv_id":"2409.18346","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["werywjw/multiclimate"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/vision-language-model-fine-tuning-via-simple","slug":"vision-language-model-fine-tuning-via-simple","title":"Vision-Language Model Fine-Tuning via Simple Parameter-Efficient Modification","date":"2024-09-25","arxiv_id":"2409.16718","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["minglllli/clipfit"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/attention-prompting-on-image-for-large-vision","slug":"attention-prompting-on-image-for-large-vision","title":"Attention Prompting on Image for Large Vision-Language Models","date":"2024-09-25","arxiv_id":"2409.17143","n_code_links":1,"syntology":{"ran":8,"of":12,"n_ran_checked":5,"n_instrument":3,"unverified":4,"pointer_only":2,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yu-rp/apiprompting"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/embedding-geometries-of-contrastive-language","slug":"embedding-geometries-of-contrastive-language","title":"Embedding Geometries of Contrastive Language-Image Pre-Training","date":"2024-09-19","arxiv_id":"2409.13079","n_code_links":1,"syntology":{"ran":9,"of":15,"n_ran_checked":6,"n_instrument":3,"unverified":6,"pointer_only":15,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","official":{"repos":["eify/open_clip"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/less-is-more-a-simple-yet-effective-token","slug":"less-is-more-a-simple-yet-effective-token","title":"Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs","date":"2024-09-17","arxiv_id":"2409.10994","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":4,"n_instrument":4,"unverified":0,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["freedomintelligence/trim"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/playground-v3-improving-text-to-image","slug":"playground-v3-improving-text-to-image","title":"Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models","date":"2024-09-16","arxiv_id":"2409.10695","n_code_links":1,"syntology":{"ran":18,"of":21,"n_ran_checked":9,"n_instrument":9,"unverified":3,"pointer_only":21,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 1 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/improving-virtual-try-on-with-garment-focused","slug":"improving-virtual-try-on-with-garment-focused","title":"Improving Virtual Try-On with Garment-focused Diffusion Models","date":"2024-09-12","arxiv_id":"2409.08258","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["siqi0905/gardiff"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/detailclip-detail-oriented-clip-for-fine","slug":"detailclip-detail-oriented-clip-for-fine","title":"DetailCLIP: Detail-Oriented CLIP for Fine-Grained Tasks","date":"2024-09-10","arxiv_id":"2409.06809","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":2,"n_instrument":4,"unverified":5,"pointer_only":11,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","official":{"repos":["KishoreP1/DetailCLIP"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/optimizing-clip-models-for-image-retrieval","slug":"optimizing-clip-models-for-image-retrieval","title":"Optimizing CLIP Models for Image Retrieval with Maintained Joint-Embedding Alignment","date":"2024-09-03","arxiv_id":"2409.01936","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":11,"n_instrument":0,"unverified":3,"pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 3 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["Visual-Computing/MCIP"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/tempme-video-temporal-token-merging-for","slug":"tempme-video-temporal-token-merging-for","title":"TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval","date":"2024-09-02","arxiv_id":"2409.01156","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":4,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/nemesis-normalizing-the-soft-prompt-vectors","slug":"nemesis-normalizing-the-soft-prompt-vectors","title":"Nemesis: Normalizing the Soft-prompt Vectors of Vision-Language Models","date":"2024-08-26","arxiv_id":"2408.13979","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":0,"n_instrument":3,"unverified":3,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["shyfoo/nemesis"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/swiftbrush-v2-make-your-one-step-diffusion","slug":"swiftbrush-v2-make-your-one-step-diffusion","title":"SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher","date":"2024-08-26","arxiv_id":"2408.14176","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vinairesearch/swiftbrushv2"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/social-perception-of-faces-in-a-vision","slug":"social-perception-of-faces-in-a-vision","title":"Social perception of faces in a vision-language model","date":"2024-08-26","arxiv_id":"2408.14435","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["carinahausladen/clip-face-bias"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/generalizable-facial-expression-recognition","slug":"generalizable-facial-expression-recognition","title":"Generalizable Facial Expression Recognition","date":"2024-08-20","arxiv_id":"2408.10614","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zyh-uaiaaaa/generalizable-fer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/c2p-clip-injecting-category-common-prompt-in","slug":"c2p-clip-injecting-category-common-prompt-in","title":"C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection","date":"2024-08-19","arxiv_id":"2408.09647","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["chuangchuangtan/c2p-clip-deepfakedetection"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/reclip-learn-to-rectify-the-bias-of-clip-for","slug":"reclip-learn-to-rectify-the-bias-of-clip-for","title":"ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation","date":"2024-08-13","arxiv_id":"2408.06747","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["dogehhh/reclip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/proxyclip-proxy-attention-improves-clip-for","slug":"proxyclip-proxy-attention-improves-clip-for","title":"ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation","date":"2024-08-09","arxiv_id":"2408.04883","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":4,"n_instrument":2,"unverified":3,"pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["mc-lan/proxyclip"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/ensemble-everything-everywhere-multi-scale","slug":"ensemble-everything-everywhere-multi-scale","title":"Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness","date":"2024-08-08","arxiv_id":"2408.05446","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["stanislavfort/ensemble-everything-everywhere"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/moextend-tuning-new-experts-for-modality-and","slug":"moextend-tuning-new-experts-for-modality-and","title":"MoExtend: Tuning New Experts for Modality and Task Extension","date":"2024-08-07","arxiv_id":"2408.03511","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zhongshsh/moextend"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/2408-02484","slug":"2408-02484","title":"Exploring Conditional Multi-Modal Prompts for Zero-shot HOI Detection","date":"2024-08-05","arxiv_id":"2408.02484","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ltttpku/cmmp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/2408-01978","slug":"2408-01978","title":"AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning","date":"2024-08-04","arxiv_id":"2408.01978","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["xinwong/advqdet"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/2408-01181","slug":"2408-01181","title":"VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling","date":"2024-08-02","arxiv_id":"2408.01181","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":4,"n_instrument":5,"unverified":4,"pointer_only":13,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","official":{"repos":["daixiangzi/var-clip"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/focus-distinguish-and-prompt-unleashing-clip","slug":"focus-distinguish-and-prompt-unleashing-clip","title":"Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval","date":"2024-08-01","arxiv_id":"2408.00441","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gyann-z/fdp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/diffusion-feedback-helps-clip-see-better","slug":"diffusion-feedback-helps-clip-see-better","title":"Diffusion Feedback Helps CLIP See Better","date":"2024-07-29","arxiv_id":"2407.20171","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["baaivision/diva"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/contrasting-deepfakes-diffusion-via","slug":"contrasting-deepfakes-diffusion-via","title":"Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities","date":"2024-07-29","arxiv_id":"2407.20337","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["aimagelab/code"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/adversarial-robustification-via-text-to-image","slug":"adversarial-robustification-via-text-to-image","title":"Adversarial Robustification via Text-to-Image Diffusion Models","date":"2024-07-26","arxiv_id":"2407.18658","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["choidae1/robustify-t2i"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-label-cluster-discrimination-for-visual","slug":"multi-label-cluster-discrimination-for-visual","title":"Multi-label Cluster Discrimination for Visual Representation Learning","date":"2024-07-24","arxiv_id":"2407.17331","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result","official":{"repos":["deepglint/unicom"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/seds-semantically-enhanced-dual-stream","slug":"seds-semantically-enhanced-dual-stream","title":"SEDS: Semantically Enhanced Dual-Stream Encoder for Sign Language Retrieval","date":"2024-07-23","arxiv_id":"2407.16394","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["longtaojiang/seds"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/category-extensible-out-of-distribution-1","slug":"category-extensible-out-of-distribution-1","title":"Category-Extensible Out-of-Distribution Detection via Hierarchical Context Descriptions","date":"2024-07-23","arxiv_id":"2407.16725","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":0,"n_instrument":3,"unverified":2,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alibaba/catex"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/compbench-a-comparative-reasoning-benchmark","slug":"compbench-a-comparative-reasoning-benchmark","title":"MLLM-CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs","date":"2024-07-23","arxiv_id":"2407.16837","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["raptormai/compbench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/clip-with-generative-latent-replay-a-strong","slug":"clip-with-generative-latent-replay-a-strong","title":"CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning","date":"2024-07-22","arxiv_id":"2407.15793","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":5,"n_instrument":3,"unverified":0,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["aimagelab/mammoth"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/adaclip-adapting-clip-with-hybrid-learnable","slug":"adaclip-adapting-clip-with-hybrid-learnable","title":"AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection","date":"2024-07-22","arxiv_id":"2407.15795","n_code_links":1,"syntology":{"ran":20,"of":28,"n_ran_checked":16,"n_instrument":4,"unverified":8,"pointer_only":4,"phrase":"20 ran (of which 10 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","official":{"repos":["caoyunkang/adaclip"],"state":"official (archive's flag): 20 ran","n_ran":20,"n_constructed":10,"n_ran_no_instrument_failure":16,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/prior-knowledge-integration-via-llm-encoding","slug":"prior-knowledge-integration-via-llm-encoding","title":"Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval","date":"2024-07-21","arxiv_id":"2407.15051","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":5,"n_instrument":3,"unverified":3,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["fletcherjiang/llmepet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/class-incremental-learning-with-clip-adaptive","slug":"class-incremental-learning-with-clip-adaptive","title":"Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion","date":"2024-07-19","arxiv_id":"2407.14143","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["linlany/rapf"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/robust-calibration-of-large-vision-language","slug":"robust-calibration-of-large-vision-language","title":"Robust Calibration of Large Vision-Language Adapters","date":"2024-07-18","arxiv_id":"2407.13588","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["Bala93/CLIPCalib"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/imagdressing-v1-customizable-virtual-dressing","slug":"imagdressing-v1-customizable-virtual-dressing","title":"IMAGDressing-v1: Customizable Virtual Dressing","date":"2024-07-17","arxiv_id":"2407.12705","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["muzishen/imagdressing"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/lami-detr-open-vocabulary-detection-with","slug":"lami-detr-open-vocabulary-detection-with","title":"LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction","date":"2024-07-16","arxiv_id":"2407.11335","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eternaldolphin/lami-detr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/single-layer-single-gradient-unlearning","slug":"single-layer-single-gradient-unlearning","title":"Unlearning Targeted Information via Single Layer Unlearning Gradient","date":"2024-07-16","arxiv_id":"2407.11867","n_code_links":1,"syntology":{"ran":16,"of":24,"n_ran_checked":12,"n_instrument":4,"unverified":8,"pointer_only":24,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","official":{"repos":["CSIPlab/slug"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/accessing-vision-foundation-models-at","slug":"accessing-vision-foundation-models-at","title":"Accessing Vision Foundation Models at ImageNet-level Costs","date":"2024-07-15","arxiv_id":"2407.10366","n_code_links":1,"syntology":{"ran":4,"of":10,"n_ran_checked":3,"n_instrument":1,"unverified":6,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["bespontaneous/proteus-pytorch"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/datadream-few-shot-guided-dataset-generation","slug":"datadream-few-shot-guided-dataset-generation","title":"DataDream: Few-shot Guided Dataset Generation","date":"2024-07-15","arxiv_id":"2407.10910","n_code_links":2,"syntology":{"ran":17,"of":21,"n_ran_checked":16,"n_instrument":1,"unverified":4,"pointer_only":21,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["explainableml/datadream"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/clip-guided-networks-for-transferable","slug":"clip-guided-networks-for-transferable","title":"CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks","date":"2024-07-14","arxiv_id":"2407.10179","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ffhibnese/CGNC_Targeted_Adversarial_Attacks"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/lapt-label-driven-automated-prompt-tuning-for","slug":"lapt-label-driven-automated-prompt-tuning-for","title":"LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models","date":"2024-07-12","arxiv_id":"2407.08966","n_code_links":2,"syntology":{"ran":15,"of":17,"n_ran_checked":11,"n_instrument":4,"unverified":2,"pointer_only":4,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 2 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ybzh/lapt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/explore-the-potential-of-clip-for-training","slug":"explore-the-potential-of-clip-for-training","title":"Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation","date":"2024-07-11","arxiv_id":"2407.08268","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["leaves162/cliptrase"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/emergent-visual-semantic-hierarchies-in-image","slug":"emergent-visual-semantic-hierarchies-in-image","title":"Emergent Visual-Semantic Hierarchies in Image-Text Representations","date":"2024-07-11","arxiv_id":"2407.08521","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["TAU-VAILab/hierarcaps"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/cola-conditional-dropout-and-language-driven","slug":"cola-conditional-dropout-and-language-driven","title":"CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detection","date":"2024-07-09","arxiv_id":"2407.06780","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":3,"n_instrument":5,"unverified":3,"pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","official":{"repos":["ssecv/CoLA"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/fine-tuning-linear-layers-only-is-a-simple","slug":"fine-tuning-linear-layers-only-is-a-simple","title":"Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic","date":"2024-07-09","arxiv_id":"2407.07089","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":0,"n_instrument":3,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["kyrie-23/task_arithmetic_tangent","kyrie-23/linear_task_arithmetic"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/awt-transferring-vision-language-models-via","slug":"awt-transferring-vision-language-models-via","title":"AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation","date":"2024-07-05","arxiv_id":"2407.04603","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["MCG-NJU/AWT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/boosting-consistency-in-story-visualization","slug":"boosting-consistency-in-story-visualization","title":"Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models","date":"2024-07-02","arxiv_id":"2407.02482","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["muzishen/rcdms"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/gallop-learning-global-and-local-prompts-for","slug":"gallop-learning-global-and-local-prompts-for","title":"GalLoP: Learning Global and Local Prompts for Vision-Language Models","date":"2024-07-01","arxiv_id":"2407.01400","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["marclafon/gallop"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/evf-sam-early-vision-language-fusion-for-text","slug":"evf-sam-early-vision-language-fusion-for-text","title":"EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model","date":"2024-06-28","arxiv_id":"2406.20076","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hustvl/evf-sam"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/a-sanity-check-for-ai-generated-image","slug":"a-sanity-check-for-ai-generated-image","title":"A Sanity Check for AI-generated Image Detection","date":"2024-06-27","arxiv_id":"2406.19435","n_code_links":2,"syntology":{"ran":8,"of":8,"n_ran_checked":6,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["shilinyan99/aide"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mitigate-the-gap-investigating-approaches-for","slug":"mitigate-the-gap-investigating-approaches-for","title":"Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIP","date":"2024-06-25","arxiv_id":"2406.17639","n_code_links":1,"syntology":{"ran":16,"of":22,"n_ran_checked":10,"n_instrument":6,"unverified":6,"pointer_only":22,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 3 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified","official":{"repos":["sarahesl/alignclip"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/arboretum-a-large-multimodal-dataset-enabling","slug":"arboretum-a-large-multimodal-dataset-enabling","title":"BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity","date":"2024-06-25","arxiv_id":"2406.17720","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["baskargroup/biotrove","baskargroup/Arboretum"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/clip-decoder-zeroshot-multilabel","slug":"clip-decoder-zeroshot-multilabel","title":"CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representation","date":"2024-06-21","arxiv_id":"2406.14830","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/african-or-european-swallow-benchmarking","slug":"african-or-european-swallow-benchmarking","title":"African or European Swallow? Benchmarking Large Vision-Language Models for Fine-Grained Object Classification","date":"2024-06-20","arxiv_id":"2406.14496","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":6,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gregor-ge/foci-benchmark"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/watt-weight-average-test-time-adaption-of","slug":"watt-weight-average-test-time-adaption-of","title":"WATT: Weight Average Test-Time Adaptation of CLIP","date":"2024-06-19","arxiv_id":"2406.13875","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":0,"n_instrument":5,"unverified":2,"pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","official":{"repos":["mehrdad-noori/watt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/efficient-and-long-tailed-generalization-for","slug":"efficient-and-long-tailed-generalization-for","title":"Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model","date":"2024-06-18","arxiv_id":"2406.12638","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":0,"n_instrument":4,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["shijxcs/candle"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/adversarial-attacks-on-multimodal-agents","slug":"adversarial-attacks-on-multimodal-agents","title":"Dissecting Adversarial Robustness of Multimodal LM Agents","date":"2024-06-18","arxiv_id":"2406.12814","n_code_links":1,"syntology":{"ran":16,"of":21,"n_ran_checked":11,"n_instrument":5,"unverified":5,"pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","official":{"repos":["chenwu98/agent-attack"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/frozen-clip-a-strong-backbone-for-weakly-1","slug":"frozen-clip-a-strong-backbone-for-weakly-1","title":"Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation","date":"2024-06-17","arxiv_id":"2406.11189","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":7,"n_instrument":1,"unverified":1,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zbf1991/weclip"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-hierarchical-semantic-classification","slug":"learning-hierarchical-semantic-classification","title":"Visually Consistent Hierarchical Image Classification","date":"2024-06-17","arxiv_id":"2406.11608","n_code_links":0,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/not-all-prompts-are-made-equal-prompt-based","slug":"not-all-prompts-are-made-equal-prompt-based","title":"Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models","date":"2024-06-17","arxiv_id":"2406.12042","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["rezashkv/diffusion_pruning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/open-vocabulary-semantic-segmentation-with-4","slug":"open-vocabulary-semantic-segmentation-with-4","title":"Open-Vocabulary Semantic Segmentation with Image Embedding Balancing","date":"2024-06-14","arxiv_id":"2406.09829","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":7,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["slonetime/ebseg"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/understanding-and-mitigating-compositional","slug":"understanding-and-mitigating-compositional","title":"Understanding and Mitigating Compositional Issues in Text-to-Image Generative Models","date":"2024-06-12","arxiv_id":"2406.07844","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ArmanZarei/Mitigating-T2I-Comp-Issues"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/asyncdiff-parallelizing-diffusion-models-by","slug":"asyncdiff-parallelizing-diffusion-models-by","title":"AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising","date":"2024-06-11","arxiv_id":"2406.06911","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":2,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["czg1225/asyncdiff"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/rwkv-clip-a-robust-vision-language","slug":"rwkv-clip-a-robust-vision-language","title":"RWKV-CLIP: A Robust Vision-Language Representation Learner","date":"2024-06-11","arxiv_id":"2406.06973","n_code_links":2,"syntology":{"ran":7,"of":14,"n_ran_checked":3,"n_instrument":4,"unverified":7,"pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","official":{"repos":["deepglint/rwkv-clip"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/let-go-of-your-labels-with-unsupervised-1","slug":"let-go-of-your-labels-with-unsupervised-1","title":"Let Go of Your Labels with Unsupervised Transfer","date":"2024-06-11","arxiv_id":"2406.07236","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mlbio-epfl/turtle"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/vision-model-pre-training-on-interleaved","slug":"vision-model-pre-training-on-interleaved","title":"Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning","date":"2024-06-11","arxiv_id":"2406.07543","n_code_links":1,"syntology":{"ran":6,"of":12,"n_ran_checked":4,"n_instrument":2,"unverified":6,"pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","official":{"repos":["opengvlab/lcl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/vript-a-video-is-worth-thousands-of-words","slug":"vript-a-video-is-worth-thousands-of-words","title":"Vript: A Video Is Worth Thousands of Words","date":"2024-06-10","arxiv_id":"2406.06040","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":2,"n_instrument":2,"unverified":4,"pointer_only":8,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["mutonix/vript"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/mlcm-multistep-consistency-distillation-of","slug":"mlcm-multistep-consistency-distillation-of","title":"TLCM: Training-efficient Latent Consistency Model for Image Generation with 2-8 Steps","date":"2024-06-09","arxiv_id":"2406.05768","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["oppo-mente-lab/tlcm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/visual-text-cross-alignment-refining-the","slug":"visual-text-cross-alignment-refining-the","title":"Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models","date":"2024-06-05","arxiv_id":"2406.02915","n_code_links":1,"syntology":{"ran":8,"of":13,"n_ran_checked":0,"n_instrument":8,"unverified":5,"pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","official":{"repos":["tmlr-group/wca"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/css-contrastive-semantic-similarity-for","slug":"css-contrastive-semantic-similarity-for","title":"CSS: Contrastive Semantic Similarity for Uncertainty Quantification of LLMs","date":"2024-06-05","arxiv_id":"2406.03158","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":8,"n_instrument":1,"unverified":2,"pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["aoshuang92/css_uq_llms"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/open-yolo-3d-towards-fast-and-accurate-open","slug":"open-yolo-3d-towards-fast-and-accurate-open","title":"Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation","date":"2024-06-04","arxiv_id":"2406.02548","n_code_links":1,"syntology":{"ran":4,"of":11,"n_ran_checked":4,"n_instrument":0,"unverified":7,"pointer_only":11,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","official":{"repos":["aminebdj/openyolo3d"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/long-and-short-guidance-in-score-identity","slug":"long-and-short-guidance-in-score-identity","title":"Long and Short Guidance in Score identity Distillation for One-Step Text-to-Image Generation","date":"2024-06-03","arxiv_id":"2406.01561","n_code_links":2,"syntology":{"ran":19,"of":24,"n_ran_checked":13,"n_instrument":6,"unverified":5,"pointer_only":7,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","official":{"repos":["mingyuanzhou/sid-lsg"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["community","official"]}}},{"paper":"/paper/decomposing-and-interpreting-image","slug":"decomposing-and-interpreting-image","title":"Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP","date":"2024-06-03","arxiv_id":"2406.01583","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["sriramb-98/vit-decompose"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/cascade-clip-cascaded-vision-language","slug":"cascade-clip-cascaded-vision-language","title":"Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation","date":"2024-06-02","arxiv_id":"2406.00670","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hvision-nku/cascade-clip"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/envisioning-outlier-exposure-by-large","slug":"envisioning-outlier-exposure-by-large","title":"Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection","date":"2024-06-02","arxiv_id":"2406.00806","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tmlr-group/eoe"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/decoop-robust-prompt-tuning-with-out-of","slug":"decoop-robust-prompt-tuning-with-out-of","title":"DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection","date":"2024-06-01","arxiv_id":"2406.00345","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":3,"n_instrument":3,"unverified":3,"pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["WNJXYK/DeCoOp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/megactor-harness-the-power-of-raw-video-for","slug":"megactor-harness-the-power-of-raw-video-for","title":"MegActor: Harness the Power of Raw Video for Vivid Portrait Animation","date":"2024-05-31","arxiv_id":"2405.20851","n_code_links":2,"syntology":{"ran":13,"of":17,"n_ran_checked":11,"n_instrument":2,"unverified":4,"pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["megvii-research/megactor","megvii-research/megfaceanimate"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/generalization-beyond-data-imbalance-a","slug":"generalization-beyond-data-imbalance-a","title":"What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights","date":"2024-05-31","arxiv_id":"2405.21070","n_code_links":1,"syntology":{"ran":5,"of":12,"n_ran_checked":3,"n_instrument":2,"unverified":7,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","official":{"repos":["cvmi-lab/clip-beyond-tail"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/enhancing-zero-shot-facial-expression","slug":"enhancing-zero-shot-facial-expression","title":"Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer","date":"2024-05-29","arxiv_id":"2405.19100","n_code_links":1,"syntology":{"ran":3,"of":10,"n_ran_checked":0,"n_instrument":3,"unverified":7,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","official":{"repos":["zengqunzhao/exp-clip"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/cliploss-and-norm-based-data-selection","slug":"cliploss-and-norm-based-data-selection","title":"CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning","date":"2024-05-29","arxiv_id":"2405.19547","n_code_links":2,"syntology":{"ran":14,"of":19,"n_ran_checked":13,"n_instrument":1,"unverified":5,"pointer_only":19,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 3 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["ypwang61/negcliploss_normsim","ypwang61/VAS"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/why-are-visually-grounded-language-models-bad","slug":"why-are-visually-grounded-language-models-bad","title":"Why are Visually-Grounded Language Models Bad at Image Classification?","date":"2024-05-28","arxiv_id":"2405.18415","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yuhui-zh15/vlmclassifier"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/benchmarking-and-improving-bird-s-eye-view","slug":"benchmarking-and-improving-bird-s-eye-view","title":"Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving","date":"2024-05-27","arxiv_id":"2405.17426","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["Daniel-xsy/RoboBEV"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/accelerating-transformers-with-spectrum-1","slug":"accelerating-transformers-with-spectrum-1","title":"Accelerating Transformers with Spectrum-Preserving Token Merging","date":"2024-05-25","arxiv_id":"2405.16148","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":2,"n_instrument":4,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hchautran/PiToMe"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-invariant-causal-mechanism-from","slug":"learning-invariant-causal-mechanism-from","title":"Learning Invariant Causal Mechanism from Vision-Language Models","date":"2024-05-24","arxiv_id":"2405.15289","n_code_links":0,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/clipscope-enhancing-zero-shot-ood-detection","slug":"clipscope-enhancing-zero-shot-ood-detection","title":"CLIPScope: Enhancing Zero-Shot OOD Detection with Bayesian Scoring","date":"2024-05-23","arxiv_id":"2405.14737","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["fu1001hao/clipscope"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/gmmformer-v2-an-uncertainty-aware-framework","slug":"gmmformer-v2-an-uncertainty-aware-framework","title":"GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrieval","date":"2024-05-22","arxiv_id":"2405.13824","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":10,"n_instrument":0,"unverified":0,"pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["huangmozhi9527/gmmformer_v2"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/topa-extend-large-language-models-for-video","slug":"topa-extend-large-language-models-for-video","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","date":"2024-05-22","arxiv_id":"2405.13911","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":4,"n_instrument":2,"unverified":3,"pointer_only":3,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["dhg-wei/topa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/harmonizing-generalization-and","slug":"harmonizing-generalization-and","title":"Harmonizing Generalization and Personalization in Federated Prompt Learning","date":"2024-05-16","arxiv_id":"2405.09771","n_code_links":1,"syntology":{"ran":7,"of":14,"n_ran_checked":3,"n_instrument":4,"unverified":7,"pointer_only":14,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","official":{"repos":["tianyucuiovo/fedpgp"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/diffam-diffusion-based-adversarial-makeup","slug":"diffam-diffusion-based-adversarial-makeup","title":"DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection","date":"2024-05-16","arxiv_id":"2405.09882","n_code_links":2,"syntology":{"ran":12,"of":14,"n_ran_checked":9,"n_instrument":3,"unverified":2,"pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["hanssuny/diffam"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/pre-trained-text-to-image-diffusion-models","slug":"pre-trained-text-to-image-diffusion-models","title":"Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control","date":"2024-05-09","arxiv_id":"2405.05852","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ykarmesh/stable-control-representations"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/openess-event-based-semantic-scene","slug":"openess-event-based-semantic-scene","title":"OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies","date":"2024-05-08","arxiv_id":"2405.05259","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ldkong1205/openess"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/isearle-improving-textual-inversion-for-zero","slug":"isearle-improving-textual-inversion-for-zero","title":"iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval","date":"2024-05-05","arxiv_id":"2405.02951","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["miccunifi/circo"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper"]}}}],"record_sha256":"ddc8605ddf8092d6e1f99a3a240036c2b81dc351e3b42ad49f70d6bee9b60aeb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}