{"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-commonsense-reasoning","name":"Visual Commonsense Reasoning","slug":"visual-commonsense-reasoning","description_markdown":"Image source: [Visual Commonsense Reasoning](https://paperswithcode.com/dataset/vcr)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"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":65,"papers_with_code":33,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"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":8,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/visual-commonsense-reasoning-on-gd-vcr","slug":"visual-commonsense-reasoning-on-gd-vcr","dataset":"GD-VCR","dataset_url":"/dataset/gd-vcr","rows_in_archive":4,"metrics":["Accuracy","Gap (West)"],"first_row_in_archive_order":{"model":"Human","paper_title":"Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning","paper_url":"/paper/broaden-the-vision-geo-diverse-visual","paper_date":"2021-09-14","arxiv_id":"2109.06860","code_links":[{"title":"wadeyin9712/gd-vcr","url":"https://github.com/wadeyin9712/gd-vcr"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/broaden-the-vision-geo-diverse-visual#ran","syntology_url":"https://syntology.ai/paper/2109.06860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.06860"}},"official":{"repos":["wadeyin9712/gd-vcr"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/visual-commonsense-reasoning-on-vcr-q-a-dev","slug":"visual-commonsense-reasoning-on-vcr-q-a-dev","dataset":"VCR (Q-A) dev","dataset_url":"/dataset/vcr","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PEVL","paper_title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","paper_url":"/paper/pevl-position-enhanced-pre-training-and","paper_date":"2022-05-23","arxiv_id":"2205.11169","code_links":[{"title":"thunlp/pevl","url":"https://github.com/thunlp/pevl"}],"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pevl-position-enhanced-pre-training-and#ran","syntology_url":"https://syntology.ai/paper/2205.11169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11169"}},"official":{"repos":["thunlp/pevl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/visual-commonsense-reasoning-on-vcr-q-a-test","slug":"visual-commonsense-reasoning-on-vcr-q-a-test","dataset":"VCR (Q-A) test","dataset_url":"/dataset/vcr","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PEVL","paper_title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","paper_url":"/paper/pevl-position-enhanced-pre-training-and","paper_date":"2022-05-23","arxiv_id":"2205.11169","code_links":[{"title":"thunlp/pevl","url":"https://github.com/thunlp/pevl"}],"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pevl-position-enhanced-pre-training-and#ran","syntology_url":"https://syntology.ai/paper/2205.11169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11169"}},"official":{"repos":["thunlp/pevl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/visual-commonsense-reasoning-on-vcr-q-ar-dev","slug":"visual-commonsense-reasoning-on-vcr-q-ar-dev","dataset":"VCR (Q-AR) dev","dataset_url":"/dataset/vcr","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PEVL","paper_title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","paper_url":"/paper/pevl-position-enhanced-pre-training-and","paper_date":"2022-05-23","arxiv_id":"2205.11169","code_links":[{"title":"thunlp/pevl","url":"https://github.com/thunlp/pevl"}],"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pevl-position-enhanced-pre-training-and#ran","syntology_url":"https://syntology.ai/paper/2205.11169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11169"}},"official":{"repos":["thunlp/pevl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/visual-commonsense-reasoning-on-vcr-q-ar-test","slug":"visual-commonsense-reasoning-on-vcr-q-ar-test","dataset":"VCR (Q-AR) test","dataset_url":"/dataset/vcr","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PEVL","paper_title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","paper_url":"/paper/pevl-position-enhanced-pre-training-and","paper_date":"2022-05-23","arxiv_id":"2205.11169","code_links":[{"title":"thunlp/pevl","url":"https://github.com/thunlp/pevl"}],"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pevl-position-enhanced-pre-training-and#ran","syntology_url":"https://syntology.ai/paper/2205.11169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11169"}},"official":{"repos":["thunlp/pevl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/visual-commonsense-reasoning-on-vcr-qa-r-dev","slug":"visual-commonsense-reasoning-on-vcr-qa-r-dev","dataset":"VCR (QA-R) dev","dataset_url":"/dataset/vcr","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PEVL","paper_title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","paper_url":"/paper/pevl-position-enhanced-pre-training-and","paper_date":"2022-05-23","arxiv_id":"2205.11169","code_links":[{"title":"thunlp/pevl","url":"https://github.com/thunlp/pevl"}],"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pevl-position-enhanced-pre-training-and#ran","syntology_url":"https://syntology.ai/paper/2205.11169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11169"}},"official":{"repos":["thunlp/pevl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/visual-commonsense-reasoning-on-vcr-qa-r-test","slug":"visual-commonsense-reasoning-on-vcr-qa-r-test","dataset":"VCR (QA-R) test","dataset_url":"/dataset/vcr","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PEVL","paper_title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","paper_url":"/paper/pevl-position-enhanced-pre-training-and","paper_date":"2022-05-23","arxiv_id":"2205.11169","code_links":[{"title":"thunlp/pevl","url":"https://github.com/thunlp/pevl"}],"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pevl-position-enhanced-pre-training-and#ran","syntology_url":"https://syntology.ai/paper/2205.11169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11169"}},"official":{"repos":["thunlp/pevl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/scienceqa","name":"ScienceQA","full_name":"Science Question Answering","num_papers_in_archive":339},{"url":"/dataset/vcr","name":"VCR","full_name":"Visual Commonsense Reasoning","num_papers_in_archive":179},{"url":"/dataset/iconqa","name":"IconQA","full_name":"Icon Question Answering","num_papers_in_archive":42},{"url":"/dataset/whoops","name":"WHOOPS!","full_name":"","num_papers_in_archive":14},{"url":"/dataset/gd-vcr","name":"GD-VCR","full_name":"","num_papers_in_archive":6},{"url":"/dataset/polymath","name":"PolyMATH","full_name":"","num_papers_in_archive":1},{"url":"/dataset/qlevr","name":"QLEVR","full_name":"","num_papers_in_archive":1},{"url":"/dataset/visual-commonsense-immorality-benchmark","name":"Visual Commonsense Immorality benchmark","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/visual-reasoning","name":"Visual Reasoning"}],"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":65,"of":65,"of_with_code":33,"tagged_in_all":65,"counts":{"archive_papers_tagged":65,"with_a_code_link":33,"where_syntology_ran_a_sample":14,"not_listed_spam_title":0,"listed":65,"listed_where_code_ran":14,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/vilbert-pretraining-task-agnostic","slug":"vilbert-pretraining-task-agnostic","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","date":"2019-08-06","arxiv_id":"1908.02265","repositories_listed":11,"syntology":{"n":34,"n_ran":10,"n_constructed":6,"n_ran_checked":8,"n_instrument":2,"n_unverified":24,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":34,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 24 unverified","sample_list":"/paper/vilbert-pretraining-task-agnostic#ran","syntology_url":"https://syntology.ai/paper/1908.02265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.02265"}},"official":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/making-large-multimodal-models-understand","slug":"making-large-multimodal-models-understand","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","date":"2023-12-01","arxiv_id":"2312.00784","repositories_listed":4,"syntology":null},{"url":"/paper/from-recognition-to-cognition-visual","slug":"from-recognition-to-cognition-visual","title":"From Recognition to Cognition: Visual Commonsense Reasoning","date":"2018-11-27","arxiv_id":"1811.10830","repositories_listed":4,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/from-recognition-to-cognition-visual#ran","syntology_url":"https://syntology.ai/paper/1811.10830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.10830"}},"official":null}},{"url":"/paper/gpt4roi-instruction-tuning-large-language","slug":"gpt4roi-instruction-tuning-large-language","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","date":"2023-07-07","arxiv_id":"2307.03601","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/gpt4roi-instruction-tuning-large-language#ran","syntology_url":"https://syntology.ai/paper/2307.03601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.03601"}},"official":{"repos":["jshilong/gpt4roi"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vl-bert-pre-training-of-generic-visual","slug":"vl-bert-pre-training-of-generic-visual","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","date":"2019-08-22","arxiv_id":"1908.08530","repositories_listed":3,"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/vl-bert-pre-training-of-generic-visual#ran","syntology_url":"https://syntology.ai/paper/1908.08530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.08530"}},"official":{"repos":["jackroos/VL-BERT"],"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/x-modaler-a-versatile-and-high-performance","slug":"x-modaler-a-versatile-and-high-performance","title":"X-modaler: A Versatile and High-performance Codebase for Cross-modal Analytics","date":"2021-08-18","arxiv_id":"2108.08217","repositories_listed":2,"syntology":null},{"url":"/paper/unifying-vision-and-language-tasks-via-text","slug":"unifying-vision-and-language-tasks-via-text","title":"Unifying Vision-and-Language Tasks via Text Generation","date":"2021-02-04","arxiv_id":"2102.02779","repositories_listed":2,"syntology":{"n":12,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/unifying-vision-and-language-tasks-via-text#ran","syntology_url":"https://syntology.ai/paper/2102.02779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.02779"}},"official":{"repos":["j-min/VL-T5"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":10,"ran_from_kinds":["official"]}}},{"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/learning-to-correction-explainable-feedback","slug":"learning-to-correction-explainable-feedback","title":"Learning to Correction: Explainable Feedback Generation for Visual Commonsense Reasoning Distractor","date":"2024-12-08","arxiv_id":"2412.07801","repositories_listed":1,"syntology":null},{"url":"/paper/improving-visual-commonsense-in-language","slug":"improving-visual-commonsense-in-language","title":"Improving Visual Commonsense in Language Models via Multiple Image Generation","date":"2024-06-19","arxiv_id":"2406.13621","repositories_listed":1,"syntology":null},{"url":"/paper/dragonfly-multi-resolution-zoom-supercharges","slug":"dragonfly-multi-resolution-zoom-supercharges","title":"Dragonfly: Multi-Resolution Zoom-In Encoding Enhances Vision-Language Models","date":"2024-06-03","arxiv_id":"2406.00977","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/dragonfly-multi-resolution-zoom-supercharges#ran","syntology_url":"https://syntology.ai/paper/2406.00977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00977"}},"official":{"repos":["togethercomputer/dragonfly"],"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/a-survey-on-interpretable-cross-modal","slug":"a-survey-on-interpretable-cross-modal","title":"A Survey on Interpretable Cross-modal Reasoning","date":"2023-09-05","arxiv_id":"2309.01955","repositories_listed":1,"syntology":null},{"url":"/paper/fusing-pre-trained-language-models-with","slug":"fusing-pre-trained-language-models-with","title":"Fusing Pre-Trained Language Models With Multimodal Prompts Through Reinforcement Learning","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vasr-visual-analogies-of-situation","slug":"vasr-visual-analogies-of-situation","title":"VASR: Visual Analogies of Situation Recognition","date":"2022-12-08","arxiv_id":"2212.04542","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/vasr-visual-analogies-of-situation#ran","syntology_url":"https://syntology.ai/paper/2212.04542","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04542"}},"official":{"repos":["vasr-dataset/vasr"],"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/learn-to-explain-multimodal-reasoning-via","slug":"learn-to-explain-multimodal-reasoning-via","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","date":"2022-09-20","arxiv_id":"2209.09513","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learn-to-explain-multimodal-reasoning-via#ran","syntology_url":"https://syntology.ai/paper/2209.09513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.09513"}},"official":{"repos":["lupantech/ScienceQA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/illume-rationalizing-vision-language-models","slug":"illume-rationalizing-vision-language-models","title":"ILLUME: Rationalizing Vision-Language Models through Human Interactions","date":"2022-08-17","arxiv_id":"2208.08241","repositories_listed":1,"syntology":null},{"url":"/paper/pevl-position-enhanced-pre-training-and","slug":"pevl-position-enhanced-pre-training-and","title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","date":"2022-05-23","arxiv_id":"2205.11169","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pevl-position-enhanced-pre-training-and#ran","syntology_url":"https://syntology.ai/paper/2205.11169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11169"}},"official":{"repos":["thunlp/pevl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/vl-interpret-an-interactive-visualization","slug":"vl-interpret-an-interactive-visualization","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","date":"2022-03-30","arxiv_id":"2203.17247","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vl-interpret-an-interactive-visualization#ran","syntology_url":"https://syntology.ai/paper/2203.17247","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.17247"}},"official":{"repos":["intellabs/vl-interpret"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/all-in-one-exploring-unified-video-language","slug":"all-in-one-exploring-unified-video-language","title":"All in One: Exploring Unified Video-Language Pre-training","date":"2022-03-14","arxiv_id":"2203.07303","repositories_listed":1,"syntology":null},{"url":"/paper/joint-answering-and-explanation-for-visual","slug":"joint-answering-and-explanation-for-visual","title":"Joint Answering and Explanation for Visual Commonsense Reasoning","date":"2022-02-25","arxiv_id":"2202.12626","repositories_listed":1,"syntology":null},{"url":"/paper/wenlan-2-0-make-ai-imagine-via-a-multimodal","slug":"wenlan-2-0-make-ai-imagine-via-a-multimodal","title":"Towards artificial general intelligence via a multimodal foundation model","date":"2021-10-27","arxiv_id":"2110.14378","repositories_listed":1,"syntology":null},{"url":"/paper/broaden-the-vision-geo-diverse-visual","slug":"broaden-the-vision-geo-diverse-visual","title":"Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning","date":"2021-09-14","arxiv_id":"2109.06860","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/broaden-the-vision-geo-diverse-visual#ran","syntology_url":"https://syntology.ai/paper/2109.06860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.06860"}},"official":{"repos":["wadeyin9712/gd-vcr"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/interpretable-visual-understanding-with","slug":"interpretable-visual-understanding-with","title":"Interpretable Visual Understanding with Cognitive Attention Network","date":"2021-08-06","arxiv_id":"2108.02924","repositories_listed":1,"syntology":null},{"url":"/paper/cognitive-visual-commonsense-reasoning-using","slug":"cognitive-visual-commonsense-reasoning-using","title":"Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory","date":"2021-07-04","arxiv_id":"2107.01671","repositories_listed":1,"syntology":null},{"url":"/paper/merlot-multimodal-neural-script-knowledge","slug":"merlot-multimodal-neural-script-knowledge","title":"MERLOT: Multimodal Neural Script Knowledge Models","date":"2021-06-04","arxiv_id":"2106.02636","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/merlot-multimodal-neural-script-knowledge#ran","syntology_url":"https://syntology.ai/paper/2106.02636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02636"}},"official":null}},{"url":"/paper/natural-language-rationales-with-full-stack","slug":"natural-language-rationales-with-full-stack","title":"Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs","date":"2020-10-15","arxiv_id":"2010.07526","repositories_listed":1,"syntology":null},{"url":"/paper/connective-cognition-network-for-directional","slug":"connective-cognition-network-for-directional","title":"Connective Cognition Network for Directional Visual Commonsense Reasoning","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tab-vcr-tags-and-attributes-based-vcr-1","slug":"tab-vcr-tags-and-attributes-based-vcr-1","title":"TAB-VCR: Tags and Attributes based VCR Baselines","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tab-vcr-tags-and-attributes-based-vcr","slug":"tab-vcr-tags-and-attributes-based-vcr","title":"TAB-VCR: Tags and Attributes based Visual Commonsense Reasoning Baselines","date":"2019-10-31","arxiv_id":"1910.14671","repositories_listed":1,"syntology":null},{"url":"/paper/heterogeneous-graph-learning-for-visual","slug":"heterogeneous-graph-learning-for-visual","title":"Heterogeneous Graph Learning for Visual Commonsense Reasoning","date":"2019-10-25","arxiv_id":"1910.11475","repositories_listed":1,"syntology":null},{"url":"/paper/fusion-of-detected-objects-in-text-for-visual","slug":"fusion-of-detected-objects-in-text-for-visual","title":"Fusion of Detected Objects in Text for Visual Question Answering","date":"2019-08-14","arxiv_id":"1908.05054","repositories_listed":1,"syntology":null},{"url":"/paper/think-visually-question-answering-through","slug":"think-visually-question-answering-through","title":"Think Visually: Question Answering through Virtual Imagery","date":"2018-05-25","arxiv_id":"1805.11025","repositories_listed":1,"syntology":null},{"url":null,"slug":"compositional-image-text-matching-and","title":"Compositional Image-Text Matching and Retrieval by Grounding Entities","date":"2025-05-04","arxiv_id":"2505.02278","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-visual-commonsense-answering-and","title":"Generative Visual Commonsense Answering and Explaining with Generative Scene Graph Constructing","date":"2025-01-15","arxiv_id":"2501.09041","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-vision-language-tasks-benefit-from-large","title":"How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey","date":"2024-12-11","arxiv_id":"2412.08158","repositories_listed":0,"syntology":null},{"url":null,"slug":"commonsense-t2i-challenge-can-text-to-image","title":"Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?","date":"2024-06-11","arxiv_id":"2406.07546","repositories_listed":0,"syntology":null},{"url":null,"slug":"algo-object-grounded-visual-commonsense","title":"ALGO: Object-Grounded Visual Commonsense Reasoning for Open-World Egocentric Action Recognition","date":"2024-06-09","arxiv_id":"2406.05722","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-vision-language-transformers-exhibit","title":"Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR","date":"2024-05-27","arxiv_id":"2405.16934","repositories_listed":0,"syntology":null},{"url":null,"slug":"eventlens-leveraging-event-aware-pretraining","title":"EventLens: Leveraging Event-Aware Pretraining and Cross-modal Linking Enhances Visual Commonsense Reasoning","date":"2024-04-22","arxiv_id":"2404.13847","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-vision-and-language-reasoning-via","title":"Improving Vision-and-Language Reasoning via Spatial Relations Modeling","date":"2023-11-09","arxiv_id":"2311.05298","repositories_listed":0,"syntology":null},{"url":null,"slug":"vicor-bridging-visual-understanding-and","title":"ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models","date":"2023-10-09","arxiv_id":"2310.05872","repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-novel-actions-in-an-open-world","title":"Discovering Novel Actions from Open World Egocentric Videos with Object-Grounded Visual Commonsense Reasoning","date":"2023-05-26","arxiv_id":"2305.16602","repositories_listed":0,"syntology":null},{"url":null,"slug":"grill-grounded-vision-language-pre-training","title":"GRILL: Grounded Vision-language Pre-training via Aligning Text and Image Regions","date":"2023-05-24","arxiv_id":"2305.14676","repositories_listed":0,"syntology":null},{"url":null,"slug":"cavl-learning-contrastive-and-adaptive","title":"CAVL: Learning Contrastive and Adaptive Representations of Vision and Language","date":"2023-04-10","arxiv_id":"2304.04399","repositories_listed":0,"syntology":null},{"url":"/paper/breaking-common-sense-whoops-a-vision-and","slug":"breaking-common-sense-whoops-a-vision-and","title":"Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images","date":"2023-03-13","arxiv_id":"2303.07274","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-agree-on-vision-attention-for","title":"Learning to Agree on Vision Attention for Visual Commonsense Reasoning","date":"2023-02-04","arxiv_id":"2302.02117","repositories_listed":0,"syntology":null},{"url":null,"slug":"pseudo-3d-perception-transformer-with-multi","title":"Multi-modal Large Language Model Enhanced Pseudo 3D Perception Framework for Visual Commonsense Reasoning","date":"2023-01-30","arxiv_id":"2301.13335","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":"on-advances-in-text-generation-from-images","title":"On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization","date":"2022-05-24","arxiv_id":"2205.11686","repositories_listed":0,"syntology":null},{"url":null,"slug":"super-prompting-utilizing-model-independent","title":"Super-Prompting: Utilizing Model-Independent Contextual Data to Reduce Data Annotation Required in Visual Commonsense Tasks","date":"2022-04-25","arxiv_id":"2204.11922","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":"attention-mechanism-based-cognition-level","title":"Attention Mechanism based Cognition-level Scene Understanding","date":"2022-04-17","arxiv_id":"2204.08027","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":"/paper/merlot-reserve-neural-script-knowledge","slug":"merlot-reserve-neural-script-knowledge","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","date":"2022-01-07","arxiv_id":"2201.02639","repositories_listed":0,"syntology":null},{"url":null,"slug":"sgeitl-scene-graph-enhanced-image-text","title":"SGEITL: Scene Graph Enhanced Image-Text Learning for Visual Commonsense Reasoning","date":"2021-12-16","arxiv_id":"2112.08587","repositories_listed":0,"syntology":null},{"url":null,"slug":"premise-based-multimodal-reasoning-a-human","title":"Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues","date":"2021-05-15","arxiv_id":"2105.07122","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":"/paper/kvl-bert-knowledge-enhanced-visual-and","slug":"kvl-bert-knowledge-enhanced-visual-and","title":"KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual Commonsense Reasoning","date":"2020-12-13","arxiv_id":"2012.07000","repositories_listed":0,"syntology":null},{"url":null,"slug":"to-root-artificial-intelligence-deeply-in","title":"To Root Artificial Intelligence Deeply in Basic Science for a New Generation of AI","date":"2020-09-11","arxiv_id":"2009.05678","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-commonsense-graphs-reasoning-about-the","title":"VisualCOMET: Reasoning about the Dynamic Context of a Still Image","date":"2020-04-22","arxiv_id":"2004.10796","repositories_listed":0,"syntology":null},{"url":"/paper/interbert-vision-and-language-interaction-for","slug":"interbert-vision-and-language-interaction-for","title":"InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining","date":"2020-03-30","arxiv_id":"2003.13198","repositories_listed":0,"syntology":null},{"url":null,"slug":"enforcing-reasoning-in-visual-commonsense","title":"Enforcing Reasoning in Visual Commonsense Reasoning","date":"2019-10-21","arxiv_id":"1910.11124","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":"/paper/unicoder-vl-a-universal-encoder-for-vision","slug":"unicoder-vl-a-universal-encoder-for-vision","title":"Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training","date":"2019-08-16","arxiv_id":"1908.06066","repositories_listed":0,"syntology":null}],"syntology_records":14,"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":14,"papers_where_code_ran_first_page":"/task/visual-commonsense-reasoning/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-commonsense-reasoning/papers/ran/1","json":"/task/visual-commonsense-reasoning/papers/ran/1.json","rows":14}],"description_links":{"kept":1,"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":"6e5238b30e146495cdeaed5199be38963e32110acb047b26abbbe48f9f9727a0","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}