{"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":"/task/image-text-retrieval","name":"Image-text Retrieval","slug":"image-text-retrieval","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":248,"papers_with_code":131,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/now","name":"NoW","full_name":"Noise of Web","num_papers_in_archive":2},{"url":"/dataset/impact-patent","name":"IMPACT Patent","full_name":"A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design Patents","num_papers_in_archive":1},{"url":"/dataset/leafnet","name":"LeafNet","full_name":"LeafNet: A large-scale dataset for training image-text models in leaf disease identification","num_papers_in_archive":1},{"url":"/dataset/noise-of-web-now","name":"Noise of Web","full_name":"NoW","num_papers_in_archive":1},{"url":"/dataset/inpaintcoco","name":"InpaintCOCO","full_name":"","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":3,"rows_per_page":100,"shown":100,"of":248,"of_with_code":131,"tagged_in_all":248,"counts":{"archive_papers_tagged":248,"with_a_code_link":131,"where_syntology_ran_a_sample":49,"not_listed_spam_title":0,"listed":248,"listed_where_code_ran":49,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":43,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":43,"listed_every_run_a_failure_of_syntologys_instrument":6,"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"},"items":[{"url":"/paper/blip-bootstrapping-language-image-pre","slug":"blip-bootstrapping-language-image-pre","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","date":"2022-01-28","arxiv_id":"2201.12086","repositories_listed":9,"syntology":null},{"url":"/paper/uniter-learning-universal-image-text-1","slug":"uniter-learning-universal-image-text-1","title":"UNITER: UNiversal Image-TExt Representation Learning","date":"2019-09-25","arxiv_id":"1909.11740","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/uniter-learning-universal-image-text-1#ran","syntology_url":"https://syntology.ai/paper/1909.11740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11740"}},"official":{"repos":["ChenRocks/UNITER"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/flexivit-one-model-for-all-patch-sizes","slug":"flexivit-one-model-for-all-patch-sizes","title":"FlexiViT: One Model for All Patch Sizes","date":"2022-12-15","arxiv_id":"2212.08013","repositories_listed":6,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"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","sample_list":"/paper/flexivit-one-model-for-all-patch-sizes#ran","syntology_url":"https://syntology.ai/paper/2212.08013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08013"}},"official":{"repos":["google-research/big_vision"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/align-before-fuse-vision-and-language","slug":"align-before-fuse-vision-and-language","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","date":"2021-07-16","arxiv_id":"2107.07651","repositories_listed":6,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_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) · 1 unverified","sample_list":"/paper/align-before-fuse-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2107.07651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07651"}},"official":{"repos":["salesforce/lavis"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/scaling-up-visual-and-vision-language","slug":"scaling-up-visual-and-vision-language","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","date":"2021-02-11","arxiv_id":"2102.05918","repositories_listed":5,"syntology":{"n":10,"n_ran":8,"n_constructed":6,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"8 ran (of which 6 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","sample_list":"/paper/scaling-up-visual-and-vision-language#ran","syntology_url":"https://syntology.ai/paper/2102.05918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05918"}},"official":null}},{"url":"/paper/mplug-effective-and-efficient-vision-language","slug":"mplug-effective-and-efficient-vision-language","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","date":"2022-05-24","arxiv_id":"2205.12005","repositories_listed":3,"syntology":null},{"url":"/paper/wit-wikipedia-based-image-text-dataset-for","slug":"wit-wikipedia-based-image-text-dataset-for","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","date":"2021-03-02","arxiv_id":"2103.01913","repositories_listed":3,"syntology":null},{"url":"/paper/biomedica-an-open-biomedical-image-caption","slug":"biomedica-an-open-biomedical-image-caption","title":"BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature","date":"2025-01-13","arxiv_id":"2501.07171","repositories_listed":2,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/biomedica-an-open-biomedical-image-caption#ran","syntology_url":"https://syntology.ai/paper/2501.07171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.07171"}},"official":{"repos":["ale9806/open_clip_with_biomedica","minwoosun/biomedica-etl"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":14,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_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","sample_list":"/paper/rwkv-clip-a-robust-vision-language#ran","syntology_url":"https://syntology.ai/paper/2406.06973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06973"}},"official":{"repos":["deepglint/rwkv-clip"],"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"]}}},{"url":"/paper/m3d-advancing-3d-medical-image-analysis-with","slug":"m3d-advancing-3d-medical-image-analysis-with","title":"M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models","date":"2024-03-31","arxiv_id":"2404.00578","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/m3d-advancing-3d-medical-image-analysis-with#ran","syntology_url":"https://syntology.ai/paper/2404.00578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00578"}},"official":{"repos":["baai-dcai/m3d"],"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"]}}},{"url":"/paper/frozen-transformers-in-language-models-are","slug":"frozen-transformers-in-language-models-are","title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","date":"2023-10-19","arxiv_id":"2310.12973","repositories_listed":2,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":4,"n_honours":3,"n_violates":1,"n_no_contract":3,"n_pointer_only":8,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/frozen-transformers-in-language-models-are#ran","syntology_url":"https://syntology.ai/paper/2310.12973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12973"}},"official":{"repos":["ziqipang/lm4visualencoding"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/esa-external-space-attention-aggregation-for","slug":"esa-external-space-attention-aggregation-for","title":"ESA: External Space Attention Aggregation for Image-Text Retrieval","date":"2023-10-10","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/contrasting-intra-modal-and-ranking-cross","slug":"contrasting-intra-modal-and-ranking-cross","title":"Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding","date":"2023-06-15","arxiv_id":"2306.08832","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/contrasting-intra-modal-and-ranking-cross#ran","syntology_url":"https://syntology.ai/paper/2306.08832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08832"}},"official":{"repos":["lezhang7/Enhance-FineGrained","magiccircuit/enhance-finegrained"],"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"]}}},{"url":"/paper/one-peace-exploring-one-general","slug":"one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":2,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}},"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/region-aware-pretraining-for-open-vocabulary","slug":"region-aware-pretraining-for-open-vocabulary","title":"Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers","date":"2023-05-11","arxiv_id":"2305.07011","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/region-aware-pretraining-for-open-vocabulary#ran","syntology_url":"https://syntology.ai/paper/2305.07011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07011"}},"official":{"repos":["mcahny/rovit","google-research/google-research"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/hyperbolic-image-text-representations","slug":"hyperbolic-image-text-representations","title":"Hyperbolic Image-Text Representations","date":"2023-04-18","arxiv_id":"2304.09172","repositories_listed":2,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":15,"phrase":"12 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; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hyperbolic-image-text-representations#ran","syntology_url":"https://syntology.ai/paper/2304.09172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.09172"}},"official":{"repos":["facebookresearch/meru"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["found_in_text","listed"]}}},{"url":"/paper/atomic-an-image-text-retrieval-test","slug":"atomic-an-image-text-retrieval-test","title":"AToMiC: An Image/Text Retrieval Test Collection to Support Multimedia Content Creation","date":"2023-04-04","arxiv_id":"2304.01961","repositories_listed":2,"syntology":null},{"url":"/paper/pmc-clip-contrastive-language-image-pre","slug":"pmc-clip-contrastive-language-image-pre","title":"PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents","date":"2023-03-13","arxiv_id":"2303.07240","repositories_listed":2,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"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","sample_list":"/paper/pmc-clip-contrastive-language-image-pre#ran","syntology_url":"https://syntology.ai/paper/2303.07240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.07240"}},"official":{"repos":["WeixiongLin/PMC-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"]}}},{"url":"/paper/uniadapter-unified-parameter-efficient","slug":"uniadapter-unified-parameter-efficient","title":"UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling","date":"2023-02-13","arxiv_id":"2302.06605","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":10,"phrase":"8 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; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/uniadapter-unified-parameter-efficient#ran","syntology_url":"https://syntology.ai/paper/2302.06605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.06605"}},"official":{"repos":["rerv/uniadapter","uniadapter/uniadapter"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/upop-unified-and-progressive-pruning-for","slug":"upop-unified-and-progressive-pruning-for","title":"UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers","date":"2023-01-31","arxiv_id":"2301.13741","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/upop-unified-and-progressive-pruning-for#ran","syntology_url":"https://syntology.ai/paper/2301.13741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13741"}},"official":{"repos":["sdc17/upop"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/hada-a-graph-based-amalgamation-framework-in","slug":"hada-a-graph-based-amalgamation-framework-in","title":"HADA: A Graph-based Amalgamation Framework in Image-text Retrieval","date":"2023-01-11","arxiv_id":"2301.04742","repositories_listed":2,"syntology":null},{"url":"/paper/dissecting-deep-metric-learning-losses-for","slug":"dissecting-deep-metric-learning-losses-for","title":"Dissecting Deep Metric Learning Losses for Image-Text Retrieval","date":"2022-10-21","arxiv_id":"2210.13188","repositories_listed":2,"syntology":null},{"url":"/paper/vlmo-unified-vision-language-pre-training","slug":"vlmo-unified-vision-language-pre-training","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","date":"2021-11-03","arxiv_id":"2111.02358","repositories_listed":2,"syntology":null},{"url":"/paper/lightningdot-pre-training-visual-semantic","slug":"lightningdot-pre-training-visual-semantic","title":"LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval","date":"2021-03-16","arxiv_id":"2103.08784","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_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","sample_list":"/paper/lightningdot-pre-training-visual-semantic#ran","syntology_url":"https://syntology.ai/paper/2103.08784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.08784"}},"official":{"repos":["intersun/LightningDOT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/gloria-a-multimodal-global-local","slug":"gloria-a-multimodal-global-local","title":"GLoRIA: A Multimodal Global-Local Representation Learning Framework for Label-Efficient Medical Image Recognition","date":"2021-01-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/large-scale-adversarial-training-for-vision","slug":"large-scale-adversarial-training-for-vision","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","date":"2020-06-11","arxiv_id":"2006.06195","repositories_listed":2,"syntology":{"n":20,"n_ran":12,"n_constructed":5,"n_ran_checked":9,"n_instrument":3,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":8,"phrase":"12 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/large-scale-adversarial-training-for-vision#ran","syntology_url":"https://syntology.ai/paper/2006.06195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06195"}},"official":{"repos":["zhegan27/LXMERT-AdvTrain","zhegan27/VILLA"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":9,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/the-neuro-symbolic-concept-learner-1","slug":"the-neuro-symbolic-concept-learner-1","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","date":"2019-04-26","arxiv_id":"1904.12584","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_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) · 2 unverified","sample_list":"/paper/the-neuro-symbolic-concept-learner-1#ran","syntology_url":"https://syntology.ai/paper/1904.12584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.12584"}},"official":{"repos":["vacancy/NSCL-PyTorch-Release"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/adding-simple-structure-at-inference-improves","slug":"adding-simple-structure-at-inference-improves","title":"Adding simple structure at inference improves Vision-Language Compositionality","date":"2025-06-11","arxiv_id":"2506.09691","repositories_listed":1,"syntology":null},{"url":"/paper/flagevalmm-a-flexible-framework-for","slug":"flagevalmm-a-flexible-framework-for","title":"FlagEvalMM: A Flexible Framework for Comprehensive Multimodal Model Evaluation","date":"2025-06-10","arxiv_id":"2506.09081","repositories_listed":1,"syntology":null},{"url":"/paper/attacking-attention-of-foundation-models","slug":"attacking-attention-of-foundation-models","title":"Attacking Attention of Foundation Models Disrupts Downstream Tasks","date":"2025-06-03","arxiv_id":"2506.05394","repositories_listed":1,"syntology":null},{"url":"/paper/a-vision-language-foundation-model-for-leaf","slug":"a-vision-language-foundation-model-for-leaf","title":"A Vision-Language Foundation Model for Leaf Disease Identification","date":"2025-05-11","arxiv_id":"2505.07019","repositories_listed":1,"syntology":null},{"url":"/paper/fg-clip-fine-grained-visual-and-textual","slug":"fg-clip-fine-grained-visual-and-textual","title":"FG-CLIP: Fine-Grained Visual and Textual Alignment","date":"2025-05-08","arxiv_id":"2505.05071","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/fg-clip-fine-grained-visual-and-textual#ran","syntology_url":"https://syntology.ai/paper/2505.05071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.05071"}},"official":{"repos":["360cvgroup/fg-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"]}}},{"url":"/paper/med3dvlm-an-efficient-vision-language-model","slug":"med3dvlm-an-efficient-vision-language-model","title":"Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis","date":"2025-03-25","arxiv_id":"2503.20047","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"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) · 5 unverified","sample_list":"/paper/med3dvlm-an-efficient-vision-language-model#ran","syntology_url":"https://syntology.ai/paper/2503.20047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.20047"}},"official":{"repos":["mirthai/med3dvlm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/mind-the-gap-benchmarking-spatial-reasoning","slug":"mind-the-gap-benchmarking-spatial-reasoning","title":"Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models","date":"2025-03-25","arxiv_id":"2503.19707","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_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) · 0 unverified","sample_list":"/paper/mind-the-gap-benchmarking-spatial-reasoning#ran","syntology_url":"https://syntology.ai/paper/2503.19707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.19707"}},"official":{"repos":["stogiannidis/srbench"],"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"]}}},{"url":"/paper/recon-enhancing-true-correspondence-1","slug":"recon-enhancing-true-correspondence-1","title":"ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning","date":"2025-02-27","arxiv_id":"2502.19962","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 1 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","sample_list":"/paper/recon-enhancing-true-correspondence-1#ran","syntology_url":"https://syntology.ai/paper/2502.19962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19962"}},"official":{"repos":["qxzha/ReCon"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/siglip-2-multilingual-vision-language","slug":"siglip-2-multilingual-vision-language","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","date":"2025-02-20","arxiv_id":"2502.14786","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-working-memory-query-guided-segment","slug":"temporal-working-memory-query-guided-segment","title":"Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding","date":"2025-02-09","arxiv_id":"2502.06020","repositories_listed":1,"syntology":null},{"url":"/paper/reversed-in-time-a-novel-temporal-emphasized","slug":"reversed-in-time-a-novel-temporal-emphasized","title":"Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval","date":"2024-12-26","arxiv_id":"2412.19178","repositories_listed":1,"syntology":null},{"url":"/paper/i0t-embedding-standardization-method-towards","slug":"i0t-embedding-standardization-method-towards","title":"I0T: Embedding Standardization Method Towards Zero Modality Gap","date":"2024-12-18","arxiv_id":"2412.14384","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-of-medical-vision-and-language","slug":"a-survey-of-medical-vision-and-language","title":"A Survey of Medical Vision-and-Language Applications and Their Techniques","date":"2024-11-19","arxiv_id":"2411.12195","repositories_listed":1,"syntology":null},{"url":"/paper/nearest-neighbor-normalization-improves","slug":"nearest-neighbor-normalization-improves","title":"Nearest Neighbor Normalization Improves Multimodal Retrieval","date":"2024-10-31","arxiv_id":"2410.24114","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-vision-language-pre-training-for","slug":"multilingual-vision-language-pre-training-for","title":"Multilingual Vision-Language Pre-training for the Remote Sensing Domain","date":"2024-10-30","arxiv_id":"2410.23370","repositories_listed":1,"syntology":null},{"url":"/paper/gssf-generalized-structural-sparse-function","slug":"gssf-generalized-structural-sparse-function","title":"GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning","date":"2024-10-20","arxiv_id":"2410.15266","repositories_listed":1,"syntology":null},{"url":"/paper/from-unimodal-to-multimodal-scaling-up","slug":"from-unimodal-to-multimodal-scaling-up","title":"From Unimodal to Multimodal: Scaling up Projectors to Align Modalities","date":"2024-09-28","arxiv_id":"2409.19425","repositories_listed":1,"syntology":null},{"url":"/paper/pc-2-pseudo-classification-based-pseudo","slug":"pc-2-pseudo-classification-based-pseudo","title":"PC$^2$: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval","date":"2024-08-02","arxiv_id":"2408.01349","repositories_listed":1,"syntology":null},{"url":"/paper/fico-itr-bridging-fine-grained-and-coarse","slug":"fico-itr-bridging-fine-grained-and-coarse","title":"FiCo-ITR: bridging fine-grained and coarse-grained image-text retrieval for comparative performance analysis","date":"2024-07-29","arxiv_id":"2407.20114","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":7,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_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","sample_list":"/paper/multi-label-cluster-discrimination-for-visual#ran","syntology_url":"https://syntology.ai/paper/2407.17331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17331"}},"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"]}}},{"url":"/paper/object-aware-query-perturbation-for-cross","slug":"object-aware-query-perturbation-for-cross","title":"Object-Aware Query Perturbation for Cross-Modal Image-Text Retrieval","date":"2024-07-17","arxiv_id":"2407.12346","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/object-aware-query-perturbation-for-cross#ran","syntology_url":"https://syntology.ai/paper/2407.12346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12346"}},"official":{"repos":["nec-n-sogi/query-perturbation"],"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"]}}},{"url":"/paper/ugncl-uncertainty-guided-noisy-correspondence","slug":"ugncl-uncertainty-guided-noisy-correspondence","title":"UGNCL: Uncertainty-Guided Noisy Correspondence Learning for Efficient Cross-Modal Matching","date":"2024-07-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cvlue-a-new-benchmark-dataset-for-chinese","slug":"cvlue-a-new-benchmark-dataset-for-chinese","title":"CVLUE: A New Benchmark Dataset for Chinese Vision-Language Understanding Evaluation","date":"2024-07-01","arxiv_id":"2407.01081","repositories_listed":1,"syntology":null},{"url":"/paper/improving-the-consistency-in-cross-lingual","slug":"improving-the-consistency-in-cross-lingual","title":"Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learning","date":"2024-06-26","arxiv_id":"2406.18254","repositories_listed":1,"syntology":null},{"url":"/paper/composing-object-relations-and-attributes-for-1","slug":"composing-object-relations-and-attributes-for-1","title":"Composing Object Relations and Attributes for Image-Text Matching","date":"2024-06-17","arxiv_id":"2406.11820","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/composing-object-relations-and-attributes-for-1#ran","syntology_url":"https://syntology.ai/paper/2406.11820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11820"}},"official":{"repos":["vkhoi/cora_cvpr24"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-vision-language-geo-foundation-model","slug":"towards-vision-language-geo-foundation-model","title":"Towards Vision-Language Geo-Foundation Model: A Survey","date":"2024-06-13","arxiv_id":"2406.09385","repositories_listed":1,"syntology":null},{"url":"/paper/transcending-fusion-a-multi-scale-alignment","slug":"transcending-fusion-a-multi-scale-alignment","title":"Transcending Fusion: A Multi-Scale Alignment Method for Remote Sensing Image-Text Retrieval","date":"2024-05-29","arxiv_id":"2405.18959","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/accelerating-transformers-with-spectrum-1#ran","syntology_url":"https://syntology.ai/paper/2405.16148","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16148"}},"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"]}}},{"url":"/paper/pir-remote-sensing-image-text-retrieval-with","slug":"pir-remote-sensing-image-text-retrieval-with","title":"PIR: Remote Sensing Image-Text Retrieval with Prior Instruction Representation Learning","date":"2024-05-16","arxiv_id":"2405.10160","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_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","sample_list":"/paper/dreamlip-language-image-pre-training-with#ran","syntology_url":"https://syntology.ai/paper/2403.17007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17007"}},"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"]}}},{"url":"/paper/eye-gaze-guided-multi-modal-alignment","slug":"eye-gaze-guided-multi-modal-alignment","title":"Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning","date":"2024-03-19","arxiv_id":"2403.12416","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/eye-gaze-guided-multi-modal-alignment#ran","syntology_url":"https://syntology.ai/paper/2403.12416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12416"}},"official":{"repos":["momarky/egma"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/cross-modal-and-uni-modal-soft-label","slug":"cross-modal-and-uni-modal-soft-label","title":"Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrieval","date":"2024-03-08","arxiv_id":"2403.05261","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/embracing-language-inclusivity-and-diversity#ran","syntology_url":"https://syntology.ai/paper/2401.17186","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17186"}},"official":{"repos":["yangbang18/clfm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-image-text-matching-with-adaptive","slug":"enhancing-image-text-matching-with-adaptive","title":"Enhancing Image-Text Matching with Adaptive Feature Aggregation","date":"2024-01-18","arxiv_id":"2401.09725","repositories_listed":1,"syntology":null},{"url":"/paper/mllms-augmented-visual-language","slug":"mllms-augmented-visual-language","title":"MLLMs-Augmented Visual-Language Representation Learning","date":"2023-11-30","arxiv_id":"2311.18765","repositories_listed":1,"syntology":null},{"url":"/paper/a-prior-instruction-representation-framework","slug":"a-prior-instruction-representation-framework","title":"A Prior Instruction Representation Framework for Remote Sensing Image-text Retrieval","date":"2023-10-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/from-scarcity-to-efficiency-improving-clip","slug":"from-scarcity-to-efficiency-improving-clip","title":"VeCLIP: Improving CLIP Training via Visual-enriched Captions","date":"2023-10-11","arxiv_id":"2310.07699","repositories_listed":1,"syntology":null},{"url":"/paper/multiway-adapater-adapting-large-scale-multi","slug":"multiway-adapater-adapting-large-scale-multi","title":"MultiWay-Adapater: Adapting large-scale multi-modal models for scalable image-text retrieval","date":"2023-09-04","arxiv_id":"2309.01516","repositories_listed":1,"syntology":null},{"url":"/paper/towards-fast-and-accurate-image-text","slug":"towards-fast-and-accurate-image-text","title":"Towards Fast and Accurate Image-Text Retrieval with Self-Supervised Fine-Grained Alignment","date":"2023-08-27","arxiv_id":"2308.14009","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-efficient-transfer-learning-for-1","slug":"parameter-efficient-transfer-learning-for-1","title":"Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval","date":"2023-08-24","arxiv_id":"2308.12509","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/parameter-efficient-transfer-learning-for-1#ran","syntology_url":"https://syntology.ai/paper/2308.12509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12509"}},"official":{"repos":["ZhanYang-nwpu/PE-RSITR"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/alip-adaptive-language-image-pre-training","slug":"alip-adaptive-language-image-pre-training","title":"ALIP: Adaptive Language-Image Pre-training with Synthetic Caption","date":"2023-08-16","arxiv_id":"2308.08428","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"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) · 5 unverified","sample_list":"/paper/alip-adaptive-language-image-pre-training#ran","syntology_url":"https://syntology.ai/paper/2308.08428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08428"}},"official":{"repos":["deepglint/alip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/advclip-downstream-agnostic-adversarial","slug":"advclip-downstream-agnostic-adversarial","title":"AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning","date":"2023-08-14","arxiv_id":"2308.07026","repositories_listed":1,"syntology":{"n":16,"n_ran":15,"n_constructed":0,"n_ran_checked":11,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":9,"n_pointer_only":5,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/advclip-downstream-agnostic-adversarial#ran","syntology_url":"https://syntology.ai/paper/2308.07026","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07026"}},"official":{"repos":["cgcl-codes/advclip"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/set-level-guidance-attack-boosting","slug":"set-level-guidance-attack-boosting","title":"Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models","date":"2023-07-26","arxiv_id":"2307.14061","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":1,"n_ran_checked":2,"n_instrument":7,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"9 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; 7 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/set-level-guidance-attack-boosting#ran","syntology_url":"https://syntology.ai/paper/2307.14061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.14061"}},"official":{"repos":["Zoky-2020/Set-level_Guidance_Attack"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/mclip-multilingual-clip-via-cross-lingual","slug":"mclip-multilingual-clip-via-cross-lingual","title":"mCLIP: Multilingual CLIP via Cross-lingual Transfer","date":"2023-07-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/stop-pre-training-adapt-visual-language","slug":"stop-pre-training-adapt-visual-language","title":"Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages","date":"2023-06-29","arxiv_id":"2306.16774","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_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) · 0 unverified","sample_list":"/paper/stop-pre-training-adapt-visual-language#ran","syntology_url":"https://syntology.ai/paper/2306.16774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.16774"}},"official":{"repos":["yasminekaroui/clicotea"],"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"]}}},{"url":"/paper/remoteclip-a-vision-language-foundation-model","slug":"remoteclip-a-vision-language-foundation-model","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","date":"2023-06-19","arxiv_id":"2306.11029","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-token-guided-image-text-retrieval","slug":"efficient-token-guided-image-text-retrieval","title":"Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training","date":"2023-06-15","arxiv_id":"2306.08789","repositories_listed":1,"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/efficient-token-guided-image-text-retrieval#ran","syntology_url":"https://syntology.ai/paper/2306.08789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08789"}},"official":null}},{"url":"/paper/babel-imagenet-massively-multilingual","slug":"babel-imagenet-massively-multilingual","title":"Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations","date":"2023-06-14","arxiv_id":"2306.08658","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_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","sample_list":"/paper/babel-imagenet-massively-multilingual#ran","syntology_url":"https://syntology.ai/paper/2306.08658","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08658"}},"official":{"repos":["gregor-ge/babel-imagenet"],"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"]}}},{"url":"/paper/global-and-local-semantic-completion-learning","slug":"global-and-local-semantic-completion-learning","title":"Global and Local Semantic Completion Learning for Vision-Language Pre-training","date":"2023-06-12","arxiv_id":"2306.07096","repositories_listed":1,"syntology":null},{"url":"/paper/multi-modal-pre-training-for-medical-vision","slug":"multi-modal-pre-training-for-medical-vision","title":"Multi-modal Pre-training for Medical Vision-language Understanding and Generation: An Empirical Study with A New Benchmark","date":"2023-06-10","arxiv_id":"2306.06494","repositories_listed":1,"syntology":null},{"url":"/paper/visualgptscore-visio-linguistic-reasoning","slug":"visualgptscore-visio-linguistic-reasoning","title":"Revisiting the Role of Language Priors in Vision-Language Models","date":"2023-06-02","arxiv_id":"2306.01879","repositories_listed":1,"syntology":null},{"url":"/paper/crossget-cross-guided-ensemble-of-tokens-for","slug":"crossget-cross-guided-ensemble-of-tokens-for","title":"CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers","date":"2023-05-27","arxiv_id":"2305.17455","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_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) · 2 unverified","sample_list":"/paper/crossget-cross-guided-ensemble-of-tokens-for#ran","syntology_url":"https://syntology.ai/paper/2305.17455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17455"}},"official":{"repos":["sdc17/crossget"],"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"]}}},{"url":"/paper/integrating-listwise-ranking-into-pairwise","slug":"integrating-listwise-ranking-into-pairwise","title":"Integrating Listwise Ranking into Pairwise-based Image-Text Retrieval","date":"2023-05-26","arxiv_id":"2305.16566","repositories_listed":1,"syntology":null},{"url":"/paper/s-clip-semi-supervised-vision-language-1","slug":"s-clip-semi-supervised-vision-language-1","title":"S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions","date":"2023-05-23","arxiv_id":"2305.14095","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/s-clip-semi-supervised-vision-language-1#ran","syntology_url":"https://syntology.ai/paper/2305.14095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14095"}},"official":{"repos":["alinlab/s-clip"],"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"]}}},{"url":"/paper/enhancing-vision-language-pre-training-with","slug":"enhancing-vision-language-pre-training-with","title":"Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner","date":"2023-05-19","arxiv_id":"2305.11769","repositories_listed":1,"syntology":null},{"url":"/paper/from-association-to-generation-text-only","slug":"from-association-to-generation-text-only","title":"From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping","date":"2023-04-26","arxiv_id":"2304.13273","repositories_listed":1,"syntology":null},{"url":"/paper/learnable-pillar-based-re-ranking-for-image","slug":"learnable-pillar-based-re-ranking-for-image","title":"Learnable Pillar-based Re-ranking for Image-Text Retrieval","date":"2023-04-25","arxiv_id":"2304.12570","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-benchmarks-for-cross-modal-image","slug":"rethinking-benchmarks-for-cross-modal-image","title":"Rethinking Benchmarks for Cross-modal Image-text Retrieval","date":"2023-04-21","arxiv_id":"2304.10824","repositories_listed":1,"syntology":null},{"url":"/paper/image-text-retrieval-via-preserving-main","slug":"image-text-retrieval-via-preserving-main","title":"Image-text Retrieval via Preserving Main Semantics of Vision","date":"2023-04-20","arxiv_id":"2304.10254","repositories_listed":1,"syntology":null},{"url":"/paper/equivariant-similarity-for-vision-language","slug":"equivariant-similarity-for-vision-language","title":"Equivariant Similarity for Vision-Language Foundation Models","date":"2023-03-25","arxiv_id":"2303.14465","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_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","sample_list":"/paper/equivariant-similarity-for-vision-language#ran","syntology_url":"https://syntology.ai/paper/2303.14465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14465"}},"official":{"repos":["wangt-cn/eqben"],"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"]}}},{"url":"/paper/semantic-preserving-augmentation-for-robust","slug":"semantic-preserving-augmentation-for-robust","title":"Semantic-Preserving Augmentation for Robust Image-Text Retrieval","date":"2023-03-10","arxiv_id":"2303.05692","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-federated-learning-via-contrastive","slug":"multimodal-federated-learning-via-contrastive","title":"Multimodal Federated Learning via Contrastive Representation Ensemble","date":"2023-02-17","arxiv_id":"2302.08888","repositories_listed":1,"syntology":null},{"url":"/paper/differentiable-outlier-detection-enable","slug":"differentiable-outlier-detection-enable","title":"Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","date":"2023-02-11","arxiv_id":"2302.05608","repositories_listed":1,"syntology":null},{"url":"/paper/lexlip-lexicon-bottlenecked-language-image","slug":"lexlip-lexicon-bottlenecked-language-image","title":"LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval","date":"2023-02-06","arxiv_id":"2302.02908","repositories_listed":1,"syntology":null},{"url":"/paper/user-unified-semantic-enhancement-with","slug":"user-unified-semantic-enhancement-with","title":"USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval","date":"2023-01-17","arxiv_id":"2301.06844","repositories_listed":1,"syntology":null},{"url":"/paper/napreg-nouns-as-proxies-regularization-for","slug":"napreg-nouns-as-proxies-regularization-for","title":"NAPReg: Nouns As Proxies Regularization for Semantically Aware Cross-Modal Embeddings","date":"2023-01-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/lexlip-lexicon-bottlenecked-language-image-1","slug":"lexlip-lexicon-bottlenecked-language-image-1","title":"LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse Retrieval","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/are-multimodal-models-robust-to-image-and","slug":"are-multimodal-models-robust-to-image-and","title":"Benchmarking Robustness of Multimodal Image-Text Models under Distribution Shift","date":"2022-12-15","arxiv_id":"2212.08044","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/are-multimodal-models-robust-to-image-and#ran","syntology_url":"https://syntology.ai/paper/2212.08044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08044"}},"official":null}},{"url":"/paper/comclip-training-free-compositional-image-and","slug":"comclip-training-free-compositional-image-and","title":"ComCLIP: Training-Free Compositional Image and Text Matching","date":"2022-11-25","arxiv_id":"2211.13854","repositories_listed":1,"syntology":null},{"url":"/paper/seeing-what-you-miss-vision-language-pre","slug":"seeing-what-you-miss-vision-language-pre","title":"Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning","date":"2022-11-24","arxiv_id":"2211.13437","repositories_listed":1,"syntology":null},{"url":"/paper/rsvg-exploring-data-and-models-for-visual","slug":"rsvg-exploring-data-and-models-for-visual","title":"RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data","date":"2022-10-23","arxiv_id":"2210.12634","repositories_listed":1,"syntology":null},{"url":"/paper/medclip-contrastive-learning-from-unpaired","slug":"medclip-contrastive-learning-from-unpaired","title":"MedCLIP: Contrastive Learning from Unpaired Medical Images and Text","date":"2022-10-18","arxiv_id":"2210.10163","repositories_listed":1,"syntology":null},{"url":"/paper/vision-language-pre-training-basics-recent","slug":"vision-language-pre-training-basics-recent","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","date":"2022-10-17","arxiv_id":"2210.09263","repositories_listed":1,"syntology":null}],"syntology_records":40,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":49,"papers_where_code_ran_first_page":"/task/image-text-retrieval/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":3,"url":"/task/image-text-retrieval/papers/2","json":"/task/image-text-retrieval/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/image-text-retrieval/papers/3","json":"/task/image-text-retrieval/papers/3.json","rows":48},{"order":"ran","page":1,"of":1,"url":"/task/image-text-retrieval/papers/ran/1","json":"/task/image-text-retrieval/papers/ran/1.json","rows":49}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"64aea66dc9cdc40aa2feef99e5529b724e2b5a0f05dc2877245f06128b17d002","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}