{"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/visual-entailment","name":"Visual Entailment","slug":"visual-entailment","description_markdown":"Visual Entailment (VE) - is a task consisting of image-sentence pairs\r\nwhereby a premise is defined by an image, rather than a\r\nnatural language sentence as in traditional Textual Entailment tasks. The goal is to predict\r\nwhether the image semantically entails the text.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":56,"papers_with_code":33,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/visual-entailment-on-snli-ve-val","slug":"visual-entailment-on-snli-ve-val","dataset":"SNLI-VE val","dataset_url":"/dataset/snli-ve","rows_in_archive":9,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"OFA","paper_title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","paper_url":"/paper/unifying-architectures-tasks-and-modalities","paper_date":"2022-02-07","arxiv_id":"2202.03052","code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"ofa-sys/ofa","url":"https://github.com/ofa-sys/ofa"},{"title":"JHKim-snu/GVCCI","url":"https://github.com/JHKim-snu/GVCCI"},{"title":"JHKim-snu/PGA","url":"https://github.com/JHKim-snu/PGA"}],"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/unifying-architectures-tasks-and-modalities#ran","syntology_url":"https://syntology.ai/paper/2202.03052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03052"}},"official":{"repos":["ofa-sys/ofa"],"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"]}}}},{"leaderboard":"/sota/visual-entailment-on-snli-ve-test","slug":"visual-entailment-on-snli-ve-test","dataset":"SNLI-VE test","dataset_url":"/dataset/snli-ve","rows_in_archive":8,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"OFA","paper_title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","paper_url":"/paper/unifying-architectures-tasks-and-modalities","paper_date":"2022-02-07","arxiv_id":"2202.03052","code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"ofa-sys/ofa","url":"https://github.com/ofa-sys/ofa"},{"title":"JHKim-snu/GVCCI","url":"https://github.com/JHKim-snu/GVCCI"},{"title":"JHKim-snu/PGA","url":"https://github.com/JHKim-snu/PGA"}],"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/unifying-architectures-tasks-and-modalities#ran","syntology_url":"https://syntology.ai/paper/2202.03052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03052"}},"official":{"repos":["ofa-sys/ofa"],"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"]}}}},{"leaderboard":"/sota/visual-entailment-on-e-snli-ve","slug":"visual-entailment-on-e-snli-ve","dataset":"e-SNLI-VE","dataset_url":"/dataset/e-snli-ve","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"OFA-X","paper_title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","paper_url":"/paper/harnessing-the-power-of-multi-task","paper_date":"2022-12-08","arxiv_id":"2212.04231","code_links":[{"title":"ofa-x/ofa-x","url":"https://github.com/ofa-x/ofa-x"}],"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/harnessing-the-power-of-multi-task#ran","syntology_url":"https://syntology.ai/paper/2212.04231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04231"}},"official":{"repos":["ofa-x/ofa-x"],"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"]}}}}],"datasets":[{"url":"/dataset/snli-ve","name":"SNLI-VE","full_name":null,"num_papers_in_archive":117},{"url":"/dataset/vsr","name":"VSR","full_name":"Visual Spatial Reasoning","num_papers_in_archive":69},{"url":"/dataset/e-snli-ve","name":"e-SNLI-VE","full_name":"","num_papers_in_archive":16}],"subtasks":[],"parent_tasks":[{"url":"/task/natural-language-inference","name":"Natural Language Inference"}],"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":1,"rows_per_page":100,"shown":56,"of":56,"of_with_code":33,"tagged_in_all":56,"counts":{"archive_papers_tagged":56,"with_a_code_link":33,"where_syntology_ran_a_sample":12,"not_listed_spam_title":0,"listed":56,"listed_where_code_ran":12,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/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/coca-contrastive-captioners-are-image-text","slug":"coca-contrastive-captioners-are-image-text","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","date":"2022-05-04","arxiv_id":"2205.01917","repositories_listed":6,"syntology":{"n":17,"n_ran":10,"n_constructed":5,"n_ran_checked":9,"n_instrument":1,"n_unverified":7,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"10 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/coca-contrastive-captioners-are-image-text#ran","syntology_url":"https://syntology.ai/paper/2205.01917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01917"}},"official":null}},{"url":"/paper/visual-spatial-reasoning","slug":"visual-spatial-reasoning","title":"Visual Spatial Reasoning","date":"2022-04-30","arxiv_id":"2205.00363","repositories_listed":4,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":6,"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) · 3 unverified","sample_list":"/paper/visual-spatial-reasoning#ran","syntology_url":"https://syntology.ai/paper/2205.00363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.00363"}},"official":{"repos":["cambridgeltl/visual-spatial-reasoning","sohojoe/clip_visual-spatial-reasoning"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/unifying-architectures-tasks-and-modalities","slug":"unifying-architectures-tasks-and-modalities","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","date":"2022-02-07","arxiv_id":"2202.03052","repositories_listed":4,"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/unifying-architectures-tasks-and-modalities#ran","syntology_url":"https://syntology.ai/paper/2202.03052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03052"}},"official":{"repos":["ofa-sys/ofa"],"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/distilled-dual-encoder-model-for-vision","slug":"distilled-dual-encoder-model-for-vision","title":"Distilled Dual-Encoder Model for Vision-Language Understanding","date":"2021-12-16","arxiv_id":"2112.08723","repositories_listed":4,"syntology":null},{"url":"/paper/how-much-can-clip-benefit-vision-and-language","slug":"how-much-can-clip-benefit-vision-and-language","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","date":"2021-07-13","arxiv_id":"2107.06383","repositories_listed":4,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"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) · 3 unverified","sample_list":"/paper/how-much-can-clip-benefit-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2107.06383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.06383"}},"official":{"repos":["clip-vil/CLIP-ViL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/do-lvlms-understand-charts-analyzing-and","slug":"do-lvlms-understand-charts-analyzing-and","title":"Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning","date":"2023-12-15","arxiv_id":"2312.10160","repositories_listed":3,"syntology":null},{"url":"/paper/seeing-out-of-the-box-end-to-end-pre-training","slug":"seeing-out-of-the-box-end-to-end-pre-training","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","date":"2021-04-07","arxiv_id":"2104.03135","repositories_listed":3,"syntology":null},{"url":"/paper/advancing-grounded-multimodal-named-entity","slug":"advancing-grounded-multimodal-named-entity","title":"Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation","date":"2024-06-11","arxiv_id":"2406.07268","repositories_listed":2,"syntology":null},{"url":"/paper/llms-as-bridges-reformulating-grounded","slug":"llms-as-bridges-reformulating-grounded","title":"LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition","date":"2024-02-15","arxiv_id":"2402.09989","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/defeasible-visual-entailment-benchmark","slug":"defeasible-visual-entailment-benchmark","title":"Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven Optimization","date":"2024-12-19","arxiv_id":"2412.16232","repositories_listed":1,"syntology":null},{"url":"/paper/v-flute-visual-figurative-language","slug":"v-flute-visual-figurative-language","title":"Understanding Figurative Meaning through Explainable Visual Entailment","date":"2024-05-02","arxiv_id":"2405.01474","repositories_listed":1,"syntology":null},{"url":"/paper/mope-parameter-efficient-and-scalable","slug":"mope-parameter-efficient-and-scalable","title":"MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion","date":"2024-03-14","arxiv_id":"2403.10568","repositories_listed":1,"syntology":null},{"url":"/paper/veglue-testing-visual-entailment-systems-via","slug":"veglue-testing-visual-entailment-systems-via","title":"VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing","date":"2024-03-05","arxiv_id":"2403.02581","repositories_listed":1,"syntology":null},{"url":"/paper/p-laplacian-adaptation-for-generative-pre","slug":"p-laplacian-adaptation-for-generative-pre","title":"p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models","date":"2023-12-17","arxiv_id":"2312.10613","repositories_listed":1,"syntology":null},{"url":"/paper/good-questions-help-zero-shot-image-reasoning","slug":"good-questions-help-zero-shot-image-reasoning","title":"Good Questions Help Zero-Shot Image Reasoning","date":"2023-12-04","arxiv_id":"2312.01598","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/i-spy-a-metaphor-large-language-models-and","slug":"i-spy-a-metaphor-large-language-models-and","title":"I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors","date":"2023-05-24","arxiv_id":"2305.14724","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/harnessing-the-power-of-multi-task","slug":"harnessing-the-power-of-multi-task","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","date":"2022-12-08","arxiv_id":"2212.04231","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/harnessing-the-power-of-multi-task#ran","syntology_url":"https://syntology.ai/paper/2212.04231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04231"}},"official":{"repos":["ofa-x/ofa-x"],"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"]}}},{"url":"/paper/i-can-t-believe-there-s-no-images-learning","slug":"i-can-t-believe-there-s-no-images-learning","title":"I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision","date":"2022-11-17","arxiv_id":"2211.09778","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/i-can-t-believe-there-s-no-images-learning#ran","syntology_url":"https://syntology.ai/paper/2211.09778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09778"}},"official":{"repos":["allenai/close"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/map-modality-agnostic-uncertainty-aware","slug":"map-modality-agnostic-uncertainty-aware","title":"MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model","date":"2022-10-11","arxiv_id":"2210.05335","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-vision-language-pretraining-with","slug":"efficient-vision-language-pretraining-with","title":"Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment","date":"2022-08-29","arxiv_id":"2208.13628","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/efficient-vision-language-pretraining-with#ran","syntology_url":"https://syntology.ai/paper/2208.13628","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.13628"}},"official":{"repos":["mshukor/vicha"],"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/prompt-tuning-for-generative-multimodal","slug":"prompt-tuning-for-generative-multimodal","title":"Prompt Tuning for Generative Multimodal Pretrained Models","date":"2022-08-04","arxiv_id":"2208.02532","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/prompt-tuning-for-generative-multimodal#ran","syntology_url":"https://syntology.ai/paper/2208.02532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02532"}},"official":{"repos":["ofa-sys/ofa"],"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/chunk-aware-alignment-and-lexical-constraint","slug":"chunk-aware-alignment-and-lexical-constraint","title":"Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations","date":"2022-07-23","arxiv_id":"2207.11401","repositories_listed":1,"syntology":null},{"url":"/paper/mixgen-a-new-multi-modal-data-augmentation","slug":"mixgen-a-new-multi-modal-data-augmentation","title":"MixGen: A New Multi-Modal Data Augmentation","date":"2022-06-16","arxiv_id":"2206.08358","repositories_listed":1,"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/mixgen-a-new-multi-modal-data-augmentation#ran","syntology_url":"https://syntology.ai/paper/2206.08358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08358"}},"official":{"repos":["amazon-research/mix-generation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/fine-grained-visual-entailment","slug":"fine-grained-visual-entailment","title":"Fine-Grained Visual Entailment","date":"2022-03-29","arxiv_id":"2203.15704","repositories_listed":1,"syntology":null},{"url":"/paper/nlx-gpt-a-model-for-natural-language","slug":"nlx-gpt-a-model-for-natural-language","title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","date":"2022-03-09","arxiv_id":"2203.05081","repositories_listed":1,"syntology":null},{"url":"/paper/check-it-again-progressive-visual-question-1","slug":"check-it-again-progressive-visual-question-1","title":"Check It Again:Progressive Visual Question Answering via Visual Entailment","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/check-it-again-progressive-visual-question","slug":"check-it-again-progressive-visual-question","title":"Check It Again: Progressive Visual Question Answering via Visual Entailment","date":"2021-06-08","arxiv_id":"2106.04605","repositories_listed":1,"syntology":null},{"url":"/paper/visual-entailment-a-novel-task-for-fine","slug":"visual-entailment-a-novel-task-for-fine","title":"Visual Entailment: A Novel Task for Fine-Grained Image Understanding","date":"2019-01-20","arxiv_id":"1901.06706","repositories_listed":1,"syntology":null},{"url":"/paper/visual-entailment-task-for-visually-grounded","slug":"visual-entailment-task-for-visually-grounded","title":"Visual Entailment Task for Visually-Grounded Language Learning","date":"2018-11-26","arxiv_id":"1811.10582","repositories_listed":1,"syntology":null},{"url":null,"slug":"voldoger-llm-assisted-datasets-for-domain","title":"VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks","date":"2024-07-29","arxiv_id":"2407.19795","repositories_listed":0,"syntology":null},{"url":null,"slug":"arcsin-adaptive-ranged-cosine-similarity","title":"ArcSin: Adaptive ranged cosine Similarity injected noise for Language-Driven Visual Tasks","date":"2024-02-27","arxiv_id":"2402.17298","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-in-context-tuning-for-multimodal","title":"Lightweight In-Context Tuning for Multimodal Unified Models","date":"2023-10-08","arxiv_id":"2310.05109","repositories_listed":0,"syntology":null},{"url":null,"slug":"let-s-not-quote-out-of-context-unified-vision","title":"\"Let's not Quote out of Context\": Unified Vision-Language Pretraining for Context Assisted Image Captioning","date":"2023-06-01","arxiv_id":"2306.00931","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-and-constructing-latent","title":"Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning","date":"2023-03-10","arxiv_id":"2303.05952","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-multimodal-multitask-multilingual","title":"Few-shot Multimodal Multitask Multilingual Learning","date":"2023-02-19","arxiv_id":"2303.12489","repositories_listed":0,"syntology":null},{"url":null,"slug":"compound-tokens-channel-fusion-for-vision","title":"Compound Tokens: Channel Fusion for Vision-Language Representation Learning","date":"2022-12-02","arxiv_id":"2212.01447","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-knowledge-enhanced-multimodal","title":"A survey on knowledge-enhanced multimodal learning","date":"2022-11-19","arxiv_id":"2211.12328","repositories_listed":0,"syntology":null},{"url":null,"slug":"alignve-visual-entailment-recognition-based","title":"AlignVE: Visual Entailment Recognition Based on Alignment Relations","date":"2022-11-16","arxiv_id":"2211.08736","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-training-image-language-transformers-for","title":"Pre-training image-language transformers for open-vocabulary tasks","date":"2022-09-09","arxiv_id":"2209.04372","repositories_listed":0,"syntology":null},{"url":null,"slug":"answer-me-multi-task-open-vocabulary-visual","title":"Answer-Me: Multi-Task Open-Vocabulary Visual Question Answering","date":"2022-05-02","arxiv_id":"2205.00949","repositories_listed":0,"syntology":null},{"url":"/paper/multimodal-adaptive-distillation-for","slug":"multimodal-adaptive-distillation-for","title":"Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks","date":"2022-04-22","arxiv_id":"2204.10496","repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-models-are-few-shot-learners-empirical","title":"CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment","date":"2022-03-14","arxiv_id":"2203.07190","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-vision-and-language-pre-training","title":"Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment","date":"2022-03-01","arxiv_id":"2203.00242","repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-td-clip-targeted-distillation-for-vision","title":"CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks","date":"2022-01-15","arxiv_id":"2201.05729","repositories_listed":0,"syntology":null},{"url":null,"slug":"logically-at-the-factify-2022-multimodal-fact","title":"Logically at Factify 2022: Multimodal Fact Verification","date":"2021-12-16","arxiv_id":"2112.09253","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-multimodal-pre-training-and-prompt","title":"Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and Generation","date":"2021-12-10","arxiv_id":"2112.05587","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-much-can-clip-benefit-vision-and-language-1","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-inter-modality-visual-parsing-with","title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training","date":"2021-06-25","arxiv_id":"2106.13488","repositories_listed":0,"syntology":null},{"url":"/paper/probing-inter-modality-visual-parsing-with-1","slug":"probing-inter-modality-visual-parsing-with-1","title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-and-Language Pre-training","date":"2021-05-21","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"playing-lottery-tickets-with-vision-and","title":"Playing Lottery Tickets with Vision and Language","date":"2021-04-23","arxiv_id":"2104.11832","repositories_listed":0,"syntology":null},{"url":null,"slug":"uniter-learning-universal-image-text","title":"UNITER: Learning UNiversal Image-TExt Representations","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"segment-phrase-table-for-semantic","title":"Segment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing","date":"2015-09-27","arxiv_id":"1509.08075","repositories_listed":0,"syntology":null}],"syntology_records":13,"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":12,"papers_where_code_ran_first_page":"/task/visual-entailment/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":"ran","page":1,"of":1,"url":"/task/visual-entailment/papers/ran/1","json":"/task/visual-entailment/papers/ran/1.json","rows":12}],"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":"54225012077f48393799727350a4fef4f1c669a59e7835b90c1ba1c9163fa766","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}