{"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/3","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":3,"pages_in_order":7,"rows_per_page":100,"rows":[201,300],"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/2","next":"/method/clip/papers/ran/4","papers":[{"paper":"/paper/on-the-test-time-zero-shot-generalization-of","slug":"on-the-test-time-zero-shot-generalization-of","title":"On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?","date":"2024-05-03","arxiv_id":"2405.02266","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":["maxzanella/mta"],"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/on-mechanistic-knowledge-localization-in-text","slug":"on-mechanistic-knowledge-localization-in-text","title":"On Mechanistic Knowledge Localization in Text-to-Image Generative Models","date":"2024-05-02","arxiv_id":"2405.01008","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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) · 0 unverified","official":{"repos":["samyadeepbasu/locogen"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/clipartt-light-weight-adaptation-of-clip-to","slug":"clipartt-light-weight-adaptation-of-clip-to","title":"CLIPArTT: Adaptation of CLIP to New Domains at Test Time","date":"2024-05-01","arxiv_id":"2405.00754","n_code_links":1,"syntology":{"ran":11,"of":15,"n_ran_checked":6,"n_instrument":5,"unverified":4,"pointer_only":15,"phrase":"11 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; 5 where Syntology's instrument failed) · 4 unverified","official":{"repos":["dosowiechi/clipartt"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/understanding-multimodal-contrastive-learning-1","slug":"understanding-multimodal-contrastive-learning-1","title":"Weighted Point Cloud Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric","date":"2024-04-30","arxiv_id":"2404.19228","n_code_links":0,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 4 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) · 2 unverified","official":null}},{"paper":"/paper/revisiting-the-adversarial-robustness-of","slug":"revisiting-the-adversarial-robustness-of","title":"Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective","date":"2024-04-30","arxiv_id":"2404.19287","n_code_links":1,"syntology":{"ran":18,"of":22,"n_ran_checked":12,"n_instrument":6,"unverified":4,"pointer_only":5,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ellezwq/mmcoa"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/modeling-caption-diversity-in-contrastive","slug":"modeling-caption-diversity-in-contrastive","title":"Modeling Caption Diversity in Contrastive Vision-Language Pretraining","date":"2024-04-30","arxiv_id":"2405.00740","n_code_links":1,"syntology":{"ran":14,"of":22,"n_ran_checked":10,"n_instrument":4,"unverified":8,"pointer_only":22,"phrase":"14 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; 4 where Syntology's instrument failed) · 8 unverified","official":{"repos":["facebookresearch/llip"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-modal-proxy-learning-towards","slug":"multi-modal-proxy-learning-towards","title":"Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering","date":"2024-04-24","arxiv_id":"2404.15655","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":1,"n_instrument":3,"unverified":3,"pointer_only":7,"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) · 3 unverified","official":{"repos":["alexander-yao/multi-map"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/mova-adapting-mixture-of-vision-experts-to","slug":"mova-adapting-mixture-of-vision-experts-to","title":"MoVA: Adapting Mixture of Vision Experts to Multimodal Context","date":"2024-04-19","arxiv_id":"2404.13046","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":4,"n_instrument":5,"unverified":2,"pointer_only":3,"phrase":"9 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; 5 where Syntology's instrument failed) · 2 unverified","official":{"repos":["templex98/mova"],"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","unlocated"]}}},{"paper":"/paper/the-devil-is-in-the-object-boundary-towards","slug":"the-devil-is-in-the-object-boundary-towards","title":"The devil is in the object boundary: towards annotation-free instance segmentation using Foundation Models","date":"2024-04-18","arxiv_id":"2404.11957","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":["chengshiest/zip-your-clip"],"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/rankclip-ranking-consistent-language-image","slug":"rankclip-ranking-consistent-language-image","title":"RankCLIP: Ranking-Consistent Language-Image Pretraining","date":"2024-04-15","arxiv_id":"2404.09387","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":5,"n_instrument":3,"unverified":3,"pointer_only":11,"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) · 3 unverified","official":{"repos":["jam1ezhang/rankclip"],"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/leveraging-temporal-contextualization-for","slug":"leveraging-temporal-contextualization-for","title":"Leveraging Temporal Contextualization for Video Action Recognition","date":"2024-04-15","arxiv_id":"2404.09490","n_code_links":2,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["naver-ai/tc-clip"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/photo-realistic-image-restoration-in-the-wild","slug":"photo-realistic-image-restoration-in-the-wild","title":"Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models","date":"2024-04-15","arxiv_id":"2404.09732","n_code_links":2,"syntology":{"ran":8,"of":9,"n_ran_checked":5,"n_instrument":3,"unverified":1,"pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["algolzw/daclip-uir"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/amu-tuning-effective-logit-bias-for-clip","slug":"amu-tuning-effective-logit-bias-for-clip","title":"AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning","date":"2024-04-13","arxiv_id":"2404.08958","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 2 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":["tju-sjyj/amu-tuning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/pay-attention-to-your-neighbours-training","slug":"pay-attention-to-your-neighbours-training","title":"Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation","date":"2024-04-12","arxiv_id":"2404.08181","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":2,"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":["sinahmr/naclip"],"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/two-effects-one-trigger-on-the-modality-gap","slug":"two-effects-one-trigger-on-the-modality-gap","title":"Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models","date":"2024-04-11","arxiv_id":"2404.07983","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":0,"n_instrument":4,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["lmb-freiburg/two-effects-one-trigger"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/view-selection-for-3d-captioning-via","slug":"view-selection-for-3d-captioning-via","title":"View Selection for 3D Captioning via Diffusion Ranking","date":"2024-04-11","arxiv_id":"2404.07984","n_code_links":2,"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":null}},{"paper":"/paper/test-time-adaptation-with-salip-a-cascade-of","slug":"test-time-adaptation-with-salip-a-cascade-of","title":"Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation","date":"2024-04-09","arxiv_id":"2404.06362","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":7,"n_instrument":2,"unverified":3,"pointer_only":5,"phrase":"9 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; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["aleemsidra/SaLIP"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/pure-turning-polysemantic-neurons-into-pure","slug":"pure-turning-polysemantic-neurons-into-pure","title":"PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits","date":"2024-04-09","arxiv_id":"2404.06453","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 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":["maxdreyer/pure"],"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/to-cool-or-not-to-cool-temperature-network","slug":"to-cool-or-not-to-cool-temperature-network","title":"To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO","date":"2024-04-06","arxiv_id":"2404.04575","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":2,"n_instrument":3,"unverified":3,"pointer_only":8,"phrase":"5 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; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["zhqiu/tempnet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/is-clip-the-main-roadblock-for-fine-grained","slug":"is-clip-the-main-roadblock-for-fine-grained","title":"Is CLIP the main roadblock for fine-grained open-world perception?","date":"2024-04-04","arxiv_id":"2404.03539","n_code_links":2,"syntology":{"ran":15,"of":17,"n_ran_checked":12,"n_instrument":3,"unverified":2,"pointer_only":17,"phrase":"15 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["lorebianchi98/fg-clip"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/no-zero-shot-without-exponential-data","slug":"no-zero-shot-without-exponential-data","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","date":"2024-04-04","arxiv_id":"2404.04125","n_code_links":1,"syntology":{"ran":8,"of":14,"n_ran_checked":8,"n_instrument":0,"unverified":6,"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) · 6 unverified","official":{"repos":["bethgelab/frequency_determines_performance"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/lp-a-surprisingly-strong-linear-probe-for-few","slug":"lp-a-surprisingly-strong-linear-probe-for-few","title":"LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP","date":"2024-04-02","arxiv_id":"2404.02285","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 0 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":["fereshteshakeri/fewshot-clip-strong-baseline"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/do-vision-language-models-understand-compound","slug":"do-vision-language-models-understand-compound","title":"Do Vision-Language Models Understand Compound Nouns?","date":"2024-03-30","arxiv_id":"2404.00419","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: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sonalkum/compun"],"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/clap4clip-continual-learning-with","slug":"clap4clip-continual-learning-with","title":"CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models","date":"2024-03-28","arxiv_id":"2403.19137","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":5,"phrase":"3 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["srvcodes/clap4clip"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/beyond-embeddings-the-promise-of-visual-table","slug":"beyond-embeddings-the-promise-of-visual-table","title":"Beyond Embeddings: The Promise of Visual Table in Visual Reasoning","date":"2024-03-27","arxiv_id":"2403.18252","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":6,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lavi-lab/visual-table"],"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/imagenet-d-benchmarking-neural-network","slug":"imagenet-d-benchmarking-neural-network","title":"ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object","date":"2024-03-27","arxiv_id":"2403.18775","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["chenshuang-zhang/imagenet_d"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/dual-memory-networks-a-versatile-adaptation","slug":"dual-memory-networks-a-versatile-adaptation","title":"Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models","date":"2024-03-26","arxiv_id":"2403.17589","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":3,"n_instrument":4,"unverified":3,"pointer_only":4,"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":["ybzh/dmn"],"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/omnivid-a-generative-framework-for-universal","slug":"omnivid-a-generative-framework-for-universal","title":"OmniVid: A Generative Framework for Universal Video Understanding","date":"2024-03-26","arxiv_id":"2403.17935","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":11,"phrase":"7 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; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["wangjk666/omnivid"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/make-your-anchor-a-diffusion-based-2d-avatar","slug":"make-your-anchor-a-diffusion-based-2d-avatar","title":"Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework","date":"2024-03-25","arxiv_id":"2403.16510","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":4,"n_instrument":2,"unverified":2,"pointer_only":8,"phrase":"6 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ictmcg/make-your-anchor"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/dreamlip-language-image-pre-training-with","slug":"dreamlip-language-image-pre-training-with","title":"DreamLIP: Language-Image Pre-training with Long Captions","date":"2024-03-25","arxiv_id":"2403.17007","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":3,"n_instrument":2,"unverified":3,"pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["zyf0619sjtu/DreamLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/continuous-subject-specific-attribute-control","slug":"continuous-subject-specific-attribute-control","title":"Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions","date":"2024-03-25","arxiv_id":"2403.17064","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":["compvis/attribute-control"],"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/task2box-box-embeddings-for-modeling","slug":"task2box-box-embeddings-for-modeling","title":"Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships","date":"2024-03-25","arxiv_id":"2403.17173","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 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":["cvl-umass/task2box"],"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/long-clip-unlocking-the-long-text-capability","slug":"long-clip-unlocking-the-long-text-capability","title":"Long-CLIP: Unlocking the Long-Text Capability of CLIP","date":"2024-03-22","arxiv_id":"2403.15378","n_code_links":1,"syntology":{"ran":8,"of":15,"n_ran_checked":5,"n_instrument":3,"unverified":7,"pointer_only":10,"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) · 7 unverified","official":{"repos":["beichenzbc/long-clip"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/llava-prumerge-adaptive-token-reduction-for","slug":"llava-prumerge-adaptive-token-reduction-for","title":"LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models","date":"2024-03-22","arxiv_id":"2403.15388","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":null}},{"paper":"/paper/c-tpt-calibrated-test-time-prompt-tuning-for","slug":"c-tpt-calibrated-test-time-prompt-tuning-for","title":"C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion","date":"2024-03-21","arxiv_id":"2403.14119","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":2,"n_instrument":6,"unverified":2,"pointer_only":5,"phrase":"8 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; 6 where Syntology's instrument failed) · 2 unverified","official":{"repos":["hee-suk-yoon/c-tpt"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/otseg-multi-prompt-sinkhorn-attention-for","slug":"otseg-multi-prompt-sinkhorn-attention-for","title":"OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation","date":"2024-03-21","arxiv_id":"2403.14183","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":7,"n_instrument":3,"unverified":0,"pointer_only":10,"phrase":"10 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cubeyoung/OTSeg"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/rar-retrieving-and-ranking-augmented-mllms","slug":"rar-retrieving-and-ranking-augmented-mllms","title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","date":"2024-03-20","arxiv_id":"2403.13805","n_code_links":2,"syntology":{"ran":5,"of":7,"n_ran_checked":2,"n_instrument":3,"unverified":2,"pointer_only":3,"phrase":"5 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["liuziyu77/rar"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/adapting-visual-language-models-for","slug":"adapting-visual-language-models-for","title":"Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images","date":"2024-03-19","arxiv_id":"2403.12570","n_code_links":1,"syntology":{"ran":9,"of":15,"n_ran_checked":5,"n_instrument":4,"unverified":6,"pointer_only":6,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","official":{"repos":["mediabrain-sjtu/mvfa-ad"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/boosting-continual-learning-of-vision","slug":"boosting-continual-learning-of-vision","title":"Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters","date":"2024-03-18","arxiv_id":"2403.11549","n_code_links":2,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":4,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jiazuoyu/moe-adapters4cl"],"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"]}}},{"paper":"/paper/arc2face-a-foundation-model-of-human-faces","slug":"arc2face-a-foundation-model-of-human-faces","title":"Arc2Face: A Foundation Model for ID-Consistent Human Faces","date":"2024-03-18","arxiv_id":"2403.11641","n_code_links":3,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":3,"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) · 3 unverified","official":{"repos":["huggingface.co/FoivosPar/Arc2Face"],"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/meta-prompting-for-automating-zero-shot","slug":"meta-prompting-for-automating-zero-shot","title":"Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs","date":"2024-03-18","arxiv_id":"2403.11755","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":2,"n_instrument":3,"unverified":2,"pointer_only":3,"phrase":"5 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jmiemirza/meta-prompting"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/quality-aware-image-text-alignment-for-real","slug":"quality-aware-image-text-alignment-for-real","title":"Quality-Aware Image-Text Alignment for Real-World Image Quality Assessment","date":"2024-03-17","arxiv_id":"2403.11176","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":0,"n_instrument":3,"unverified":2,"pointer_only":5,"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":["miccunifi/qualiclip"],"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/mindeye2-shared-subject-models-enable-fmri-to","slug":"mindeye2-shared-subject-models-enable-fmri-to","title":"MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data","date":"2024-03-17","arxiv_id":"2403.11207","n_code_links":1,"syntology":{"ran":15,"of":15,"n_ran_checked":14,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 3 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["medarc-ai/mindeyev2"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/get-unlocking-the-multi-modal-potential-of","slug":"get-unlocking-the-multi-modal-potential-of","title":"Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery","date":"2024-03-15","arxiv_id":"2403.09974","n_code_links":1,"syntology":{"ran":7,"of":14,"n_ran_checked":2,"n_instrument":5,"unverified":7,"pointer_only":3,"phrase":"7 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; 5 where Syntology's instrument failed) · 7 unverified","official":{"repos":["enguangw/get"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/improving-medical-multi-modal-contrastive","slug":"improving-medical-multi-modal-contrastive","title":"Improving Medical Multi-modal Contrastive Learning with Expert Annotations","date":"2024-03-15","arxiv_id":"2403.10153","n_code_links":1,"syntology":{"ran":5,"of":12,"n_ran_checked":3,"n_instrument":2,"unverified":7,"pointer_only":12,"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) · 7 unverified","official":{"repos":["ykumards/eclip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/coleclip-open-domain-continual-learning-via","slug":"coleclip-open-domain-continual-learning-via","title":"CoLeCLIP: Open-Domain Continual Learning via Joint Task Prompt and Vocabulary Learning","date":"2024-03-15","arxiv_id":"2403.10245","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["YukunLi99/CoLeCLIP"],"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/isotropic3d-image-to-3d-generation-based-on-a","slug":"isotropic3d-image-to-3d-generation-based-on-a","title":"Isotropic3D: Image-to-3D Generation Based on a Single CLIP Embedding","date":"2024-03-15","arxiv_id":"2403.10395","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["pkunliu/isotropic3d"],"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/calibrating-multi-modal-representations-a","slug":"calibrating-multi-modal-representations-a","title":"Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations","date":"2024-03-12","arxiv_id":"2403.07241","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["charlesyou999648/cfr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/beyond-text-frozen-large-language-models-in","slug":"beyond-text-frozen-large-language-models-in","title":"Beyond Text: Frozen Large Language Models in Visual Signal Comprehension","date":"2024-03-12","arxiv_id":"2403.07874","n_code_links":1,"syntology":{"ran":17,"of":26,"n_ran_checked":6,"n_instrument":11,"unverified":9,"pointer_only":26,"phrase":"17 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; 11 where Syntology's instrument failed) · 9 unverified","official":{"repos":["zh460045050/v2l-tokenizer"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/toward-generalist-anomaly-detection-via-in","slug":"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","arxiv_id":"2403.06495","n_code_links":2,"syntology":{"ran":16,"of":21,"n_ran_checked":14,"n_instrument":2,"unverified":5,"pointer_only":16,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 1 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["mala-lab/inctrl","mala-lab/winclip"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/split-to-merge-unifying-separated-modalities","slug":"split-to-merge-unifying-separated-modalities","title":"Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation","date":"2024-03-11","arxiv_id":"2403.06946","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":6,"n_instrument":2,"unverified":1,"pointer_only":9,"phrase":"8 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tl-uestc/unimos"],"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/ella-equip-diffusion-models-with-llm-for","slug":"ella-equip-diffusion-models-with-llm-for","title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","date":"2024-03-08","arxiv_id":"2403.05135","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":2,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/peeb-part-based-image-classifiers-with-an","slug":"peeb-part-based-image-classifiers-with-an","title":"PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck","date":"2024-03-08","arxiv_id":"2403.05297","n_code_links":1,"syntology":{"ran":14,"of":21,"n_ran_checked":13,"n_instrument":1,"unverified":7,"pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","official":{"repos":["anguyen8/peeb"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-adapting-large-visual-language-models-to","slug":"self-adapting-large-visual-language-models-to","title":"Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalities","date":"2024-03-07","arxiv_id":"2403.04908","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"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) · 0 unverified","official":{"repos":["ramdrop/edgevl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/flame-diffuser-grounded-wildfire-image","slug":"flame-diffuser-grounded-wildfire-image","title":"FLAME Diffuser: Wildfire Image Synthesis using Mask Guided Diffusion","date":"2024-03-06","arxiv_id":"2403.03463","n_code_links":1,"syntology":{"ran":13,"of":16,"n_ran_checked":7,"n_instrument":6,"unverified":3,"pointer_only":16,"phrase":"13 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; 6 where Syntology's instrument failed) · 3 unverified","official":{"repos":["AIS-Clemson/FLAME_SD"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/meacap-memory-augmented-zero-shot-image","slug":"meacap-memory-augmented-zero-shot-image","title":"MeaCap: Memory-Augmented Zero-shot Image Captioning","date":"2024-03-06","arxiv_id":"2403.03715","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":4,"n_instrument":2,"unverified":4,"pointer_only":10,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["joeyz0z/meacap"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/what-do-we-learn-from-inverting-clip-models","slug":"what-do-we-learn-from-inverting-clip-models","title":"What do we learn from inverting CLIP models?","date":"2024-03-05","arxiv_id":"2403.02580","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"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) · 1 unverified","official":{"repos":["hamidkazemi22/clipinversion"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/one-prompt-word-is-enough-to-boost","slug":"one-prompt-word-is-enough-to-boost","title":"One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models","date":"2024-03-04","arxiv_id":"2403.01849","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"5 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["treelli/apt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/g3dr-generative-3d-reconstruction-in-imagenet","slug":"g3dr-generative-3d-reconstruction-in-imagenet","title":"G3DR: Generative 3D Reconstruction in ImageNet","date":"2024-03-01","arxiv_id":"2403.00939","n_code_links":1,"syntology":{"ran":8,"of":13,"n_ran_checked":8,"n_instrument":0,"unverified":5,"pointer_only":13,"phrase":"8 ran (of which 8 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) · 5 unverified; every one of the 8 samples that ran constructed an object rather than computing a result","official":{"repos":["preddy5/g3dr"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":8,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/measuring-vision-language-stem-skills-of","slug":"measuring-vision-language-stem-skills-of","title":"Measuring Vision-Language STEM Skills of Neural Models","date":"2024-02-27","arxiv_id":"2402.17205","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":["stemdataset/STEM"],"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/fine-tuning-clip-text-encoders-with-two-step","slug":"fine-tuning-clip-text-encoders-with-two-step","title":"Fine-tuning CLIP Text Encoders with Two-step Paraphrasing","date":"2024-02-23","arxiv_id":"2402.15120","n_code_links":0,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/seeing-is-believing-mitigating-hallucination","slug":"seeing-is-believing-mitigating-hallucination","title":"Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding","date":"2024-02-23","arxiv_id":"2402.15300","n_code_links":2,"syntology":{"ran":11,"of":17,"n_ran_checked":11,"n_instrument":0,"unverified":6,"pointer_only":17,"phrase":"11 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; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["d-ailin/clip-guided-decoding"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/balanced-data-sampling-for-language-model","slug":"balanced-data-sampling-for-language-model","title":"Balanced Data Sampling for Language Model Training with Clustering","date":"2024-02-22","arxiv_id":"2402.14526","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["choosewhatulike/cluster-clip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/clipping-the-deception-adapting-vision","slug":"clipping-the-deception-adapting-vision","title":"CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detection","date":"2024-02-20","arxiv_id":"2402.12927","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":["sohailahmedkhan/CLIPping-the-Deception"],"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/countercurate-enhancing-physical-and-semantic","slug":"countercurate-enhancing-physical-and-semantic","title":"CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples","date":"2024-02-20","arxiv_id":"2402.13254","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":7,"n_instrument":1,"unverified":0,"pointer_only":8,"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) · 0 unverified","official":{"repos":["hansolo9682/countercurate"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/robust-clip-unsupervised-adversarial-fine","slug":"robust-clip-unsupervised-adversarial-fine","title":"Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models","date":"2024-02-19","arxiv_id":"2402.12336","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":1,"n_instrument":6,"unverified":2,"pointer_only":0,"phrase":"7 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; 6 where Syntology's instrument failed) · 2 unverified","official":{"repos":["chs20/robustvlm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/zerog-investigating-cross-dataset-zero-shot","slug":"zerog-investigating-cross-dataset-zero-shot","title":"ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs","date":"2024-02-17","arxiv_id":"2402.11235","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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) · 0 unverified","official":{"repos":["nineabyss/zerog"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/interpreting-clip-with-sparse-linear-concept","slug":"interpreting-clip-with-sparse-linear-concept","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","date":"2024-02-16","arxiv_id":"2402.10376","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":7,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"7 ran (of which 1 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) · 3 unverified","official":{"repos":["ai4life-group/splice"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/open-vocabulary-segmentation-with-unpaired","slug":"open-vocabulary-segmentation-with-unpaired","title":"Open-Vocabulary Segmentation with Unpaired Mask-Text Supervision","date":"2024-02-14","arxiv_id":"2402.08960","n_code_links":2,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":7,"phrase":"6 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["derrickwang005/uni-ovseg.pytorch","derrickwang005/unpair-seg.pytorch"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/colorswap-a-color-and-word-order-dataset-for","slug":"colorswap-a-color-and-word-order-dataset-for","title":"ColorSwap: A Color and Word Order Dataset for Multimodal Evaluation","date":"2024-02-07","arxiv_id":"2402.04492","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["top34051/colorswap"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/ov-nerf-open-vocabulary-neural-radiance","slug":"ov-nerf-open-vocabulary-neural-radiance","title":"OV-NeRF: Open-vocabulary Neural Radiance Fields with Vision and Language Foundation Models for 3D Semantic Understanding","date":"2024-02-07","arxiv_id":"2402.04648","n_code_links":1,"syntology":{"ran":12,"of":13,"n_ran_checked":10,"n_instrument":2,"unverified":1,"pointer_only":13,"phrase":"12 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["pcl3dv/ov-nerf"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-hard-to-beat-baseline-for-training-free","slug":"a-hard-to-beat-baseline-for-training-free","title":"A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation","date":"2024-02-06","arxiv_id":"2402.04087","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":0,"n_instrument":3,"unverified":2,"pointer_only":5,"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":["mrflogs/iclr24"],"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/eva-clip-18b-scaling-clip-to-18-billion","slug":"eva-clip-18b-scaling-clip-to-18-billion","title":"EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters","date":"2024-02-06","arxiv_id":"2402.04252","n_code_links":2,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["baaivision/eva"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/enhancing-compositional-generalization-via","slug":"enhancing-compositional-generalization-via","title":"Enhancing Compositional Generalization via Compositional Feature Alignment","date":"2024-02-05","arxiv_id":"2402.02851","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"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) · 1 unverified","official":{"repos":["haoxiang-wang/compositional-feature-alignment"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/variance-alignment-score-a-simple-but-tough","slug":"variance-alignment-score-a-simple-but-tough","title":"Variance Alignment Score: A Simple But Tough-to-Beat Data Selection Method for Multimodal Contrastive Learning","date":"2024-02-03","arxiv_id":"2402.02055","n_code_links":2,"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, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/a-probabilistic-model-to-explain-self","slug":"a-probabilistic-model-to-explain-self","title":"A Probabilistic Model Behind Self-Supervised Learning","date":"2024-02-02","arxiv_id":"2402.01399","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":7,"n_instrument":2,"unverified":1,"pointer_only":10,"phrase":"9 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["alicebizeul/simvae"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/synthclip-are-we-ready-for-a-fully-synthetic","slug":"synthclip-are-we-ready-for-a-fully-synthetic","title":"SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?","date":"2024-02-02","arxiv_id":"2402.01832","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":8,"n_instrument":3,"unverified":1,"pointer_only":12,"phrase":"11 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hammoudhasan/synthclip"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/vision-llms-can-fool-themselves-with-self","slug":"vision-llms-can-fool-themselves-with-self","title":"Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks","date":"2024-02-01","arxiv_id":"2402.00626","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":3,"n_instrument":1,"unverified":4,"pointer_only":8,"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) · 4 unverified","official":{"repos":["mqraitem/self-gen-typo-attack"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/embracing-language-inclusivity-and-diversity","slug":"embracing-language-inclusivity-and-diversity","title":"Embracing Language Inclusivity and Diversity in CLIP through Continual Language Learning","date":"2024-01-30","arxiv_id":"2401.17186","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":["yangbang18/clfm"],"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/freestyle-free-lunch-for-text-guided-style","slug":"freestyle-free-lunch-for-text-guided-style","title":"FreeStyle: Free Lunch for Text-guided Style Transfer using Diffusion Models","date":"2024-01-28","arxiv_id":"2401.15636","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":3,"n_instrument":1,"unverified":3,"pointer_only":7,"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) · 3 unverified","official":{"repos":["freestylefreelunch/freestyle"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/data-free-generalized-zero-shot-learning","slug":"data-free-generalized-zero-shot-learning","title":"Data-Free Generalized Zero-Shot Learning","date":"2024-01-28","arxiv_id":"2401.15657","n_code_links":1,"syntology":{"ran":9,"of":14,"n_ran_checked":4,"n_instrument":5,"unverified":5,"pointer_only":14,"phrase":"9 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; 5 where Syntology's instrument failed) · 5 unverified","official":{"repos":["ylong4/dfzsl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/scimmir-benchmarking-scientific-multi-modal","slug":"scimmir-benchmarking-scientific-multi-modal","title":"SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval","date":"2024-01-24","arxiv_id":"2401.13478","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":8,"n_instrument":1,"unverified":1,"pointer_only":10,"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) · 1 unverified","official":{"repos":["wusiwei0410/scimmir"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/prompting-large-vision-language-models-for","slug":"prompting-large-vision-language-models-for","title":"Prompting Large Vision-Language Models for Compositional Reasoning","date":"2024-01-20","arxiv_id":"2401.11337","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":["tossowski/keycomp"],"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/dgl-dynamic-global-local-prompt-tuning-for","slug":"dgl-dynamic-global-local-prompt-tuning-for","title":"DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval","date":"2024-01-19","arxiv_id":"2401.10588","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["knightyxp/dgl"],"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":["listed","official"]}}},{"paper":"/paper/supervised-fine-tuning-in-turn-improves","slug":"supervised-fine-tuning-in-turn-improves","title":"Supervised Fine-tuning in turn Improves Visual Foundation Models","date":"2024-01-18","arxiv_id":"2401.10222","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":10,"n_instrument":0,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":{"repos":["tencentarc/visft"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/cross-modal-retrieval-for-knowledge-based","slug":"cross-modal-retrieval-for-knowledge-based","title":"Cross-modal Retrieval for Knowledge-based Visual Question Answering","date":"2024-01-11","arxiv_id":"2401.05736","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":["paullerner/viquae"],"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/eyes-wide-shut-exploring-the-visual","slug":"eyes-wide-shut-exploring-the-visual","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","date":"2024-01-11","arxiv_id":"2401.06209","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":3,"n_instrument":3,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tsb0601/MMVP"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/do-vision-and-language-encoders-represent-the","slug":"do-vision-and-language-encoders-represent-the","title":"Do Vision and Language Encoders Represent the World Similarly?","date":"2024-01-10","arxiv_id":"2401.05224","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":["mayug/0-shot-llm-vision"],"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/towards-online-sign-language-recognition-and","slug":"towards-online-sign-language-recognition-and","title":"Towards Online Continuous Sign Language Recognition and Translation","date":"2024-01-10","arxiv_id":"2401.05336","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":3,"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) · 2 unverified","official":{"repos":["FangyunWei/SLRT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/pre-trained-model-guided-fine-tuning-for-zero","slug":"pre-trained-model-guided-fine-tuning-for-zero","title":"Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness","date":"2024-01-09","arxiv_id":"2401.04350","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":7,"n_instrument":1,"unverified":2,"pointer_only":10,"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) · 2 unverified","official":{"repos":["serendipity1122/pre-trained-model-guided-fine-tuning-for-zero-shot-adversarial-robustness"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/open-vocabulary-sam-segment-and-recognize","slug":"open-vocabulary-sam-segment-and-recognize","title":"Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively","date":"2024-01-05","arxiv_id":"2401.02955","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":5,"n_instrument":2,"unverified":4,"pointer_only":11,"phrase":"7 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["harboryuan/ovsam"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/denoising-vision-transformers","slug":"denoising-vision-transformers","title":"Denoising Vision Transformers","date":"2024-01-05","arxiv_id":"2401.02957","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"6 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["Jiawei-Yang/Denoising-ViT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/latte-latent-diffusion-transformer-for-video","slug":"latte-latent-diffusion-transformer-for-video","title":"Latte: Latent Diffusion Transformer for Video Generation","date":"2024-01-05","arxiv_id":"2401.03048","n_code_links":4,"syntology":{"ran":12,"of":13,"n_ran_checked":10,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"12 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["maxin-cn/Latte"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/mining-fine-grained-image-text-alignment-for","slug":"mining-fine-grained-image-text-alignment-for","title":"Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training","date":"2024-01-04","arxiv_id":"2401.02347","n_code_links":1,"syntology":{"ran":3,"of":8,"n_ran_checked":1,"n_instrument":2,"unverified":5,"pointer_only":8,"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) · 5 unverified","official":{"repos":["artanic30/maccap"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/learning-to-prompt-with-text-only-supervision","slug":"learning-to-prompt-with-text-only-supervision","title":"Learning to Prompt with Text Only Supervision for Vision-Language Models","date":"2024-01-04","arxiv_id":"2401.02418","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":3,"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":["muzairkhattak/protext"],"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/improved-zero-shot-classification-by-adapting","slug":"improved-zero-shot-classification-by-adapting","title":"Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions","date":"2024-01-04","arxiv_id":"2401.02460","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":["cvl-umass/adaptclipzs"],"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/tinygpt-v-efficient-multimodal-large-language","slug":"tinygpt-v-efficient-multimodal-large-language","title":"TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones","date":"2023-12-28","arxiv_id":"2312.16862","n_code_links":2,"syntology":{"ran":7,"of":7,"n_ran_checked":1,"n_instrument":6,"unverified":0,"pointer_only":0,"phrase":"7 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; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dlyuangod/tinygpt-v"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-vision-from-models-rivals-learning","slug":"learning-vision-from-models-rivals-learning","title":"Learning Vision from Models Rivals Learning Vision from Data","date":"2023-12-28","arxiv_id":"2312.17742","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/syn-rep-learn"],"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/forgery-aware-adaptive-transformer-for","slug":"forgery-aware-adaptive-transformer-for","title":"Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection","date":"2023-12-27","arxiv_id":"2312.16649","n_code_links":2,"syntology":{"ran":6,"of":7,"n_ran_checked":1,"n_instrument":5,"unverified":1,"pointer_only":4,"phrase":"6 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; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["Michel-liu/FatFormer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/harmonyview-harmonizing-consistency-and","slug":"harmonyview-harmonizing-consistency-and","title":"HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D","date":"2023-12-26","arxiv_id":"2312.15980","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"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":["byeongjun-park/HarmonyView"],"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"]}}}],"record_sha256":"6b5925d131235f47e21f956871a4a602d675a53c03b08c743bb842cf2e4b7d7a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}