{"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-reasoning","name":"Visual Reasoning","slug":"visual-reasoning","description_markdown":"Ability to understand  actions and reasoning  associated with any  visual images","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":698,"papers_with_code":356,"benchmarks":12,"benchmark_tables_in_archive":12,"benchmark_tables_shown":12,"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":44,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/visual-reasoning-on-winoground","slug":"visual-reasoning-on-winoground","dataset":"Winoground","dataset_url":"/dataset/winoground","rows_in_archive":114,"metrics":["Text Score","Image Score","Group Score"],"first_row_in_archive_order":{"model":"GPT-4o + CA","paper_title":"A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs","paper_url":"/paper/cognitive-paradigms-for-evaluating-vlms-on","paper_date":"2025-01-23","arxiv_id":"2501.13620","code_links":[],"syntology":null}},{"leaderboard":"/sota/visual-reasoning-on-nlvr2-dev","slug":"visual-reasoning-on-nlvr2-dev","dataset":"NLVR2 Dev","dataset_url":"/dataset/nlvr","rows_in_archive":15,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"BEiT-3","paper_title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","paper_url":"/paper/image-as-a-foreign-language-beit-pretraining","paper_date":"2022-08-22","arxiv_id":"2208.10442","code_links":[{"title":"microsoft/unilm","url":"https://github.com/microsoft/unilm/tree/master/beit"},{"title":"lyan62/data-curation","url":"https://github.com/lyan62/data-curation"}],"syntology":null}},{"leaderboard":"/sota/visual-reasoning-on-nlvr2-test","slug":"visual-reasoning-on-nlvr2-test","dataset":"NLVR2 Test","dataset_url":"/dataset/nlvr","rows_in_archive":14,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"BEiT-3","paper_title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","paper_url":"/paper/image-as-a-foreign-language-beit-pretraining","paper_date":"2022-08-22","arxiv_id":"2208.10442","code_links":[{"title":"microsoft/unilm","url":"https://github.com/microsoft/unilm/tree/master/beit"},{"title":"lyan62/data-curation","url":"https://github.com/lyan62/data-curation"}],"syntology":null}},{"leaderboard":"/sota/visual-reasoning-on-clevrer","slug":"visual-reasoning-on-clevrer","dataset":"CLEVRER","dataset_url":null,"rows_in_archive":13,"metrics":["Average-per ques.","Descriptive","Explanatory-per opt.","Explanatory-per ques.","Predictive-per opt.","Predictive-per ques.","Counterfactual-per opt.","Counterfactual-per ques."],"first_row_in_archive_order":{"model":"AI Core","paper_title":"Think before You Simulate: Symbolic Reasoning to Orchestrate Neural Computation for Counterfactual Question Answering","paper_url":"/paper/think-before-you-simulate-symbolic-reasoning-1","paper_date":"2025-06-12","arxiv_id":"2506.10753","code_links":[{"title":"azreasoners/CRCG","url":"https://github.com/azreasoners/CRCG"}],"syntology":null}},{"leaderboard":"/sota/visual-reasoning-on-bongard-openworld","slug":"visual-reasoning-on-bongard-openworld","dataset":"Bongard-OpenWorld","dataset_url":"/dataset/bongard-openworld","rows_in_archive":9,"metrics":["2-Class Accuracy"],"first_row_in_archive_order":{"model":"Gemini-2.0 + CA","paper_title":"A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs","paper_url":"/paper/cognitive-paradigms-for-evaluating-vlms-on","paper_date":"2025-01-23","arxiv_id":"2501.13620","code_links":[],"syntology":null}},{"leaderboard":"/sota/visual-reasoning-on-winogavil","slug":"visual-reasoning-on-winogavil","dataset":"WinoGAViL","dataset_url":"/dataset/winogavil","rows_in_archive":8,"metrics":["Jaccard Index"],"first_row_in_archive_order":{"model":"Humans","paper_title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","paper_url":"/paper/winogavil-gamified-association-benchmark-to","paper_date":"2022-07-25","arxiv_id":"2207.12576","code_links":[{"title":"winogavil/winogavil-experiments","url":"https://github.com/winogavil/winogavil-experiments"}],"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/winogavil-gamified-association-benchmark-to#ran","syntology_url":"https://syntology.ai/paper/2207.12576","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.12576"}},"official":{"repos":["winogavil/winogavil-experiments"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/visual-reasoning-on-vsr","slug":"visual-reasoning-on-vsr","dataset":"VSR","dataset_url":"/dataset/vsr","rows_in_archive":5,"metrics":["accuracy"],"first_row_in_archive_order":{"model":"LXMERT","paper_title":"Visual Spatial Reasoning","paper_url":"/paper/visual-spatial-reasoning","paper_date":"2022-04-30","arxiv_id":"2205.00363","code_links":[{"title":"cambridgeltl/visual-spatial-reasoning","url":"https://github.com/cambridgeltl/visual-spatial-reasoning"},{"title":"ziyan-xiaoyu/spatialmqa","url":"https://github.com/ziyan-xiaoyu/spatialmqa"},{"title":"sohojoe/clip_visual-spatial-reasoning","url":"https://github.com/sohojoe/clip_visual-spatial-reasoning"},{"title":"MindCode-4/code-1","url":"https://github.com/MindCode-4/code-1/tree/main/vilt"}],"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"]}}}},{"leaderboard":"/sota/visual-reasoning-on-phyre-1b-cross","slug":"visual-reasoning-on-phyre-1b-cross","dataset":"PHYRE-1B-Cross","dataset_url":"/dataset/phyre","rows_in_archive":4,"metrics":["AUCCESS"],"first_row_in_archive_order":{"model":"RPIN","paper_title":"Learning Long-term Visual Dynamics with Region Proposal Interaction Networks","paper_url":"/paper/learning-long-term-visual-dynamics-with","paper_date":"2020-08-05","arxiv_id":"2008.02265","code_links":[{"title":"HaozhiQi/RPIN","url":"https://github.com/HaozhiQi/RPIN"}],"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/learning-long-term-visual-dynamics-with#ran","syntology_url":"https://syntology.ai/paper/2008.02265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.02265"}},"official":{"repos":["HaozhiQi/RPIN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/visual-reasoning-on-phyre-1b-within","slug":"visual-reasoning-on-phyre-1b-within","dataset":"PHYRE-1B-Within","dataset_url":"/dataset/phyre","rows_in_archive":4,"metrics":["AUCCESS"],"first_row_in_archive_order":{"model":"RPIN","paper_title":"Learning Long-term Visual Dynamics with Region Proposal Interaction Networks","paper_url":"/paper/learning-long-term-visual-dynamics-with","paper_date":"2020-08-05","arxiv_id":"2008.02265","code_links":[{"title":"HaozhiQi/RPIN","url":"https://github.com/HaozhiQi/RPIN"}],"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/learning-long-term-visual-dynamics-with#ran","syntology_url":"https://syntology.ai/paper/2008.02265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.02265"}},"official":{"repos":["HaozhiQi/RPIN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/visual-reasoning-on-vasr","slug":"visual-reasoning-on-vasr","dataset":"VASR","dataset_url":"/dataset/vasr","rows_in_archive":4,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"Swin","paper_title":"VASR: Visual Analogies of Situation Recognition","paper_url":"/paper/vasr-visual-analogies-of-situation","paper_date":"2022-12-08","arxiv_id":"2212.04542","code_links":[{"title":"vasr-dataset/vasr","url":"https://github.com/vasr-dataset/vasr"}],"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"]}}}},{"leaderboard":"/sota/visual-reasoning-on-irfl-image-recognition-of","slug":"visual-reasoning-on-irfl-image-recognition-of","dataset":"IRFL: Image Recognition of Figurative Language","dataset_url":"/dataset/irfl-image-recognition-of-figurative-language","rows_in_archive":1,"metrics":["1-of-100 Accuracy"],"first_row_in_archive_order":{"model":"Humans","paper_title":"IRFL: Image Recognition of Figurative Language","paper_url":"/paper/irfl-image-recognition-of-figurative-language","paper_date":"2023-03-27","arxiv_id":"2303.15445","code_links":[{"title":"irfl-dataset/irfl","url":"https://github.com/irfl-dataset/irfl"}],"syntology":null}},{"leaderboard":"/sota/visual-reasoning-on-nlvr","slug":"visual-reasoning-on-nlvr","dataset":"NLVR","dataset_url":"/dataset/nlvr","rows_in_archive":1,"metrics":["Accuracy (Dev)","Accuracy (Test-P)","Accuracy (Test-U)"],"first_row_in_archive_order":{"model":"VisualBERT","paper_title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","paper_url":"/paper/visualbert-a-simple-and-performant-baseline","paper_date":"2019-08-09","arxiv_id":"1908.03557","code_links":[{"title":"uclanlp/visualbert","url":"https://github.com/uclanlp/visualbert"},{"title":"YIKUAN8/Transformers-VQA","url":"https://github.com/YIKUAN8/Transformers-VQA"},{"title":"lalithjets/surgical_vqa","url":"https://github.com/lalithjets/surgical_vqa"},{"title":"gchhablani/multilingual-vqa","url":"https://github.com/gchhablani/multilingual-vqa"},{"title":"longbai1006/surgical-vqla","url":"https://github.com/longbai1006/surgical-vqla"},{"title":"social-ai-studio/matk","url":"https://github.com/social-ai-studio/matk"},{"title":"chenkangyang/paddle_visual_bert","url":"https://github.com/chenkangyang/paddle_visual_bert"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/5/visual_bert"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/visual_bert"},{"title":"MindCode-4/code-1","url":"https://github.com/MindCode-4/code-1/tree/main/visual_bert"}],"syntology":{"n":9,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/visualbert-a-simple-and-performant-baseline#ran","syntology_url":"https://syntology.ai/paper/1908.03557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.03557"}},"official":null}}}],"datasets":[{"url":"/dataset/refcoco","name":"RefCOCO","full_name":"","num_papers_in_archive":439},{"url":"/dataset/mathvista","name":"MathVista","full_name":"Mathematical Reasoning of in Visual Contexts","num_papers_in_archive":242},{"url":"/dataset/shapes-1","name":"SHAPES","full_name":"Swarm Heuristics based Adaptive and Penalized Estimation of Splines","num_papers_in_archive":120},{"url":"/dataset/snli-ve","name":"SNLI-VE","full_name":null,"num_papers_in_archive":117},{"url":"/dataset/textcaps","name":"TextCaps","full_name":"","num_papers_in_archive":98},{"url":"/dataset/raven","name":"RAVEN","full_name":"","num_papers_in_archive":96},{"url":"/dataset/winoground","name":"Winoground","full_name":"","num_papers_in_archive":90},{"url":"/dataset/abstractreasoning","name":"AbstractReasoning","full_name":"AbstractReasoning","num_papers_in_archive":86},{"url":"/dataset/nlvr","name":"NLVR","full_name":"Natural Language Visual Reasoningnatural language for visual reasoning","num_papers_in_archive":83},{"url":"/dataset/vsr","name":"VSR","full_name":"Visual Spatial Reasoning","num_papers_in_archive":69},{"url":"/dataset/figureqa","name":"FigureQA","full_name":"","num_papers_in_archive":61},{"url":"/dataset/pgm","name":"PGM","full_name":"Procedurally Generated Matrices (PGM)","num_papers_in_archive":57},{"url":"/dataset/cater","name":"CATER","full_name":"","num_papers_in_archive":51},{"url":"/dataset/iconqa","name":"IconQA","full_name":"Icon Question Answering","num_papers_in_archive":42},{"url":"/dataset/phyre","name":"PHYRE","full_name":"PHYsical REasoning","num_papers_in_archive":35},{"url":"/dataset/iglue","name":"IGLUE","full_name":"Image-Grounded Language Understanding Evaluation","num_papers_in_archive":31},{"url":"/dataset/marvl","name":"MaRVL","full_name":"Multicultural Reasoning over Vision and Language","num_papers_in_archive":29},{"url":"/dataset/social-iq","name":"Social-IQ","full_name":"","num_papers_in_archive":23},{"url":"/dataset/core-mm","name":"InfiMM-Eval","full_name":"Complex Open-ended Reasoning Evaluation for Multi-Modal Language Models","num_papers_in_archive":19},{"url":"/dataset/clevr-ref","name":"CLEVR-Ref+","full_name":"","num_papers_in_archive":17},{"url":"/dataset/super-clevr","name":"Super-CLEVR","full_name":"","num_papers_in_archive":13},{"url":"/dataset/cops-ref","name":"Cops-Ref","full_name":"","num_papers_in_archive":8},{"url":"/dataset/cog","name":"COG","full_name":"","num_papers_in_archive":7},{"url":"/dataset/relative-size","name":"Relative Size","full_name":"","num_papers_in_archive":6},{"url":"/dataset/smart-101","name":"SMART-101","full_name":"Simple Multimodal Algorithmic Reasoning Task Dataset","num_papers_in_archive":6},{"url":"/dataset/comphy","name":"ComPhy","full_name":"Compositional Physical Reasoning Dataset","num_papers_in_archive":5},{"url":"/dataset/kilogram","name":"KiloGram","full_name":"","num_papers_in_archive":5},{"url":"/dataset/pgdp5k","name":"PGDP5K","full_name":"Plane Geometry Diagram Parsing Dataset","num_papers_in_archive":5},{"url":"/dataset/trance","name":"TRANCE","full_name":"Transformation Driven Visual Reasoning","num_papers_in_archive":5},{"url":"/dataset/winogavil","name":"WinoGAViL","full_name":"","num_papers_in_archive":5},{"url":"/dataset/vasr","name":"VASR","full_name":"Visual Analogies of Situation Recognition","num_papers_in_archive":4},{"url":"/dataset/ade-affordance","name":"ADE-Affordance","full_name":"","num_papers_in_archive":3},{"url":"/dataset/bongard-openworld","name":"Bongard-OpenWorld","full_name":"","num_papers_in_archive":3},{"url":"/dataset/p2gb","name":"P2GB","full_name":"","num_papers_in_archive":3},{"url":"/dataset/g-vue","name":"G-VUE","full_name":"General-purpose Visual Understanding Evaluation","num_papers_in_archive":2},{"url":"/dataset/irfl-image-recognition-of-figurative-language","name":"IRFL: Image Recognition of Figurative Language","full_name":"","num_papers_in_archive":2},{"url":"/dataset/machine-number-sense","name":"Machine Number Sense","full_name":"","num_papers_in_archive":2},{"url":"/dataset/emma","name":"EMMA","full_name":"An Enhanced MultiModal ReAsoning Benchmark","num_papers_in_archive":1},{"url":"/dataset/lilgym","name":"lilGym","full_name":"","num_papers_in_archive":1},{"url":"/dataset/polymath","name":"PolyMATH","full_name":"","num_papers_in_archive":1},{"url":"/dataset/sequence-consistency-evaluation-sce-tests","name":"Sequence Consistency Evaluation (SCE) tests","full_name":"","num_papers_in_archive":1},{"url":"/dataset/svrt","name":"SVRT","full_name":"Synthetic Visual Reasoning Task","num_papers_in_archive":1},{"url":"/dataset/visual-choice-of-plausible-alternatives","name":"Visual Choice of Plausible Alternatives","full_name":"VCOPA","num_papers_in_archive":1},{"url":"/dataset/cvr-tasks","name":"Compositional Visual Reasoning (CVR)","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/visual-commonsense-reasoning","name":"Visual Commonsense Reasoning"}],"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":7,"rows_per_page":100,"shown":100,"of":698,"of_with_code":356,"tagged_in_all":698,"counts":{"archive_papers_tagged":698,"with_a_code_link":356,"where_syntology_ran_a_sample":165,"not_listed_spam_title":0,"listed":698,"listed_where_code_ran":165,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":127,"every_run_a_failure_of_syntologys_instrument":38,"listed_with_a_run_with_no_instrument_failure":127,"listed_every_run_a_failure_of_syntologys_instrument":38,"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/learning-transferable-visual-models-from","slug":"learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","arxiv_id":"2103.00020","repositories_listed":82,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":2,"n_instrument":14,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":16,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 14 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-transferable-visual-models-from#ran","syntology_url":"https://syntology.ai/paper/2103.00020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00020"}},"official":{"repos":["openai/CLIP"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/blip-2-bootstrapping-language-image-pre","slug":"blip-2-bootstrapping-language-image-pre","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","date":"2023-01-30","arxiv_id":"2301.12597","repositories_listed":17,"syntology":{"n":8,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 4 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) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/blip-2-bootstrapping-language-image-pre#ran","syntology_url":"https://syntology.ai/paper/2301.12597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12597"}},"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/visual-instruction-tuning-1","slug":"visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","arxiv_id":"2304.08485","repositories_listed":13,"syntology":{"n":51,"n_ran":16,"n_constructed":6,"n_ran_checked":8,"n_instrument":8,"n_unverified":35,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 35 unverified","sample_list":"/paper/visual-instruction-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2304.08485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08485"}},"official":{"repos":["haotian-liu/LLaVA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["community","listed","named_in_paper","official"]}}},{"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/visualbert-a-simple-and-performant-baseline","slug":"visualbert-a-simple-and-performant-baseline","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","date":"2019-08-09","arxiv_id":"1908.03557","repositories_listed":10,"syntology":{"n":9,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/visualbert-a-simple-and-performant-baseline#ran","syntology_url":"https://syntology.ai/paper/1908.03557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.03557"}},"official":null}},{"url":"/paper/compositional-attention-networks-for-machine","slug":"compositional-attention-networks-for-machine","title":"Compositional Attention Networks for Machine Reasoning","date":"2018-03-08","arxiv_id":"1803.03067","repositories_listed":10,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/compositional-attention-networks-for-machine#ran","syntology_url":"https://syntology.ai/paper/1803.03067","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.03067"}},"official":{"repos":["stanfordnlp/mac-network"],"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/vse-improving-visual-semantic-embeddings-with","slug":"vse-improving-visual-semantic-embeddings-with","title":"VSE++: Improving Visual-Semantic Embeddings with Hard Negatives","date":"2017-07-18","arxiv_id":"1707.05612","repositories_listed":10,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 3 unverified","sample_list":"/paper/vse-improving-visual-semantic-embeddings-with#ran","syntology_url":"https://syntology.ai/paper/1707.05612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.05612"}},"official":{"repos":["fartashf/vsepp"],"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/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/lxmert-learning-cross-modality-encoder","slug":"lxmert-learning-cross-modality-encoder","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","date":"2019-08-20","arxiv_id":"1908.07490","repositories_listed":9,"syntology":{"n":15,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"4 ran (of which 4 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) · 11 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/lxmert-learning-cross-modality-encoder#ran","syntology_url":"https://syntology.ai/paper/1908.07490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07490"}},"official":{"repos":["airsplay/lxmert"],"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/vinvl-making-visual-representations-matter-in","slug":"vinvl-making-visual-representations-matter-in","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","date":"2021-01-02","arxiv_id":"2101.00529","repositories_listed":7,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vinvl-making-visual-representations-matter-in#ran","syntology_url":"https://syntology.ai/paper/2101.00529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00529"}},"official":{"repos":["pzzhang/VinVL"],"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/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/film-visual-reasoning-with-a-general","slug":"film-visual-reasoning-with-a-general","title":"FiLM: Visual Reasoning with a General Conditioning Layer","date":"2017-09-22","arxiv_id":"1709.07871","repositories_listed":7,"syntology":{"n":10,"n_ran":9,"n_constructed":4,"n_ran_checked":8,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":7,"phrase":"9 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/film-visual-reasoning-with-a-general#ran","syntology_url":"https://syntology.ai/paper/1709.07871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.07871"}},"official":{"repos":["ethanjperez/film"],"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":["listed","official"]}}},{"url":"/paper/minigpt-4-enhancing-vision-language","slug":"minigpt-4-enhancing-vision-language","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","date":"2023-04-20","arxiv_id":"2304.10592","repositories_listed":6,"syntology":null},{"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/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/vilt-vision-and-language-transformer-without","slug":"vilt-vision-and-language-transformer-without","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","date":"2021-02-05","arxiv_id":"2102.03334","repositories_listed":6,"syntology":{"n":4,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/vilt-vision-and-language-transformer-without#ran","syntology_url":"https://syntology.ai/paper/2102.03334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.03334"}},"official":{"repos":["dandelin/vilt"],"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/learning-to-compose-dynamic-tree-structures","slug":"learning-to-compose-dynamic-tree-structures","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","date":"2018-12-05","arxiv_id":"1812.01880","repositories_listed":6,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-to-compose-dynamic-tree-structures#ran","syntology_url":"https://syntology.ai/paper/1812.01880","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.01880"}},"official":null}},{"url":"/paper/mmmu-a-massive-multi-discipline-multimodal","slug":"mmmu-a-massive-multi-discipline-multimodal","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","date":"2023-11-27","arxiv_id":"2311.16502","repositories_listed":5,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mmmu-a-massive-multi-discipline-multimodal#ran","syntology_url":"https://syntology.ai/paper/2311.16502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16502"}},"official":{"repos":["MMMU-Benchmark/MMMU"],"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":["listed","official","unlocated"]}}},{"url":"/paper/gqa-a-new-dataset-for-compositional-question","slug":"gqa-a-new-dataset-for-compositional-question","title":"GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering","date":"2019-02-25","arxiv_id":"1902.09506","repositories_listed":5,"syntology":null},{"url":"/paper/inferring-and-executing-programs-for-visual","slug":"inferring-and-executing-programs-for-visual","title":"Inferring and Executing Programs for Visual Reasoning","date":"2017-05-10","arxiv_id":"1705.03633","repositories_listed":5,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/inferring-and-executing-programs-for-visual#ran","syntology_url":"https://syntology.ai/paper/1705.03633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.03633"}},"official":{"repos":["facebookresearch/clevr-iep"],"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":["listed","official"]}}},{"url":"/paper/clevr-a-diagnostic-dataset-for-compositional","slug":"clevr-a-diagnostic-dataset-for-compositional","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","date":"2016-12-20","arxiv_id":"1612.06890","repositories_listed":5,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 3 unverified","sample_list":"/paper/clevr-a-diagnostic-dataset-for-compositional#ran","syntology_url":"https://syntology.ai/paper/1612.06890","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.06890"}},"official":null}},{"url":"/paper/how-is-chatgpt-s-behavior-changing-over-time","slug":"how-is-chatgpt-s-behavior-changing-over-time","title":"How is ChatGPT's behavior changing over time?","date":"2023-07-18","arxiv_id":"2307.09009","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-is-chatgpt-s-behavior-changing-over-time#ran","syntology_url":"https://syntology.ai/paper/2307.09009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09009"}},"official":{"repos":["lchen001/llmdrift"],"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":["listed","official"]}}},{"url":"/paper/your-diffusion-model-is-secretly-a-zero-shot","slug":"your-diffusion-model-is-secretly-a-zero-shot","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","date":"2023-03-28","arxiv_id":"2303.16203","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/your-diffusion-model-is-secretly-a-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2303.16203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16203"}},"official":{"repos":["diffusion-classifier/diffusion-classifier"],"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":["listed","official"]}}},{"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/flava-a-foundational-language-and-vision","slug":"flava-a-foundational-language-and-vision","title":"FLAVA: A Foundational Language And Vision Alignment Model","date":"2021-12-08","arxiv_id":"2112.04482","repositories_listed":4,"syntology":null},{"url":"/paper/learning-by-abstraction-the-neural-state","slug":"learning-by-abstraction-the-neural-state","title":"Learning by Abstraction: The Neural State Machine","date":"2019-07-09","arxiv_id":"1907.03950","repositories_listed":4,"syntology":{"n":21,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":8,"n_honours":2,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/learning-by-abstraction-the-neural-state#ran","syntology_url":"https://syntology.ai/paper/1907.03950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.03950"}},"official":{"repos":["stanfordnlp/mac-network"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mmcode-evaluating-multi-modal-code-large","slug":"mmcode-evaluating-multi-modal-code-large","title":"MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems","date":"2024-04-15","arxiv_id":"2404.09486","repositories_listed":3,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":3,"n_instrument":10,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":16,"phrase":"13 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; 10 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mmcode-evaluating-multi-modal-code-large#ran","syntology_url":"https://syntology.ai/paper/2404.09486","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09486"}},"official":{"repos":["happylkx/mmcode","likaixin2000/mmcode"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/collaborative-transformers-for-grounded","slug":"collaborative-transformers-for-grounded","title":"Collaborative Transformers for Grounded Situation Recognition","date":"2022-03-30","arxiv_id":"2203.16518","repositories_listed":3,"syntology":{"n":7,"n_ran":5,"n_constructed":3,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"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; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/collaborative-transformers-for-grounded#ran","syntology_url":"https://syntology.ai/paper/2203.16518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16518"}},"official":{"repos":["jhcho99/coformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/an-empirical-study-of-training-end-to-end","slug":"an-empirical-study-of-training-end-to-end","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","date":"2021-11-03","arxiv_id":"2111.02387","repositories_listed":3,"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":0,"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/an-empirical-study-of-training-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2111.02387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02387"}},"official":{"repos":["zdou0830/meter"],"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/visually-grounded-reasoning-across-languages","slug":"visually-grounded-reasoning-across-languages","title":"Visually Grounded Reasoning across Languages and Cultures","date":"2021-09-28","arxiv_id":"2109.13238","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/visually-grounded-reasoning-across-languages#ran","syntology_url":"https://syntology.ai/paper/2109.13238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.13238"}},"official":{"repos":["e-bug/volta","marvl-challenge/marvl-code"],"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/image-retrieval-on-real-life-images-with-pre","slug":"image-retrieval-on-real-life-images-with-pre","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","date":"2021-08-09","arxiv_id":"2108.04024","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/image-retrieval-on-real-life-images-with-pre#ran","syntology_url":"https://syntology.ai/paper/2108.04024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04024"}},"official":{"repos":["Cuberick-Orion/CIRPLANT","Cuberick-Orion/CIRR"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/clevrer-collision-events-for-video","slug":"clevrer-collision-events-for-video","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","date":"2019-10-03","arxiv_id":"1910.01442","repositories_listed":3,"syntology":null},{"url":"/paper/clevr-ref-diagnosing-visual-reasoning-with","slug":"clevr-ref-diagnosing-visual-reasoning-with","title":"CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions","date":"2019-01-03","arxiv_id":"1901.00850","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clevr-ref-diagnosing-visual-reasoning-with#ran","syntology_url":"https://syntology.ai/paper/1901.00850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.00850"}},"official":null}},{"url":"/paper/a-dataset-and-architecture-for-visual","slug":"a-dataset-and-architecture-for-visual","title":"A Dataset and Architecture for Visual Reasoning with a Working Memory","date":"2018-03-16","arxiv_id":"1803.06092","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-dataset-and-architecture-for-visual#ran","syntology_url":"https://syntology.ai/paper/1803.06092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.06092"}},"official":{"repos":["google/cog"],"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":["listed","official"]}}},{"url":"/paper/skywork-r1v3-technical-report","slug":"skywork-r1v3-technical-report","title":"Skywork-R1V3 Technical Report","date":"2025-07-08","arxiv_id":"2507.06167","repositories_listed":2,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":2,"n_instrument":9,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 9 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/skywork-r1v3-technical-report#ran","syntology_url":"https://syntology.ai/paper/2507.06167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.06167"}},"official":{"repos":["SkyworkAI/Skywork-R1V"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/from-eduvisbench-to-eduvisagent-a-benchmark","slug":"from-eduvisbench-to-eduvisagent-a-benchmark","title":"From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Pedagogical Visualization","date":"2025-05-22","arxiv_id":"2505.16832","repositories_listed":2,"syntology":null},{"url":"/paper/sota-with-less-mcts-guided-sample-selection","slug":"sota-with-less-mcts-guided-sample-selection","title":"SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement","date":"2025-04-10","arxiv_id":"2504.07934","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 0 unverified","sample_list":"/paper/sota-with-less-mcts-guided-sample-selection#ran","syntology_url":"https://syntology.ai/paper/2504.07934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07934"}},"official":{"repos":["si0wang/thinklite-vl"],"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","unlocated"]}}},{"url":"/paper/cityeqa-a-hierarchical-llm-agent-on-embodied","slug":"cityeqa-a-hierarchical-llm-agent-on-embodied","title":"CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space","date":"2025-02-18","arxiv_id":"2502.12532","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"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) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/cityeqa-a-hierarchical-llm-agent-on-embodied#ran","syntology_url":"https://syntology.ai/paper/2502.12532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.12532"}},"official":{"repos":["biluyong/cityeqa","tsinghua-fib-lab/CityEQA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/virgo-a-preliminary-exploration-on","slug":"virgo-a-preliminary-exploration-on","title":"Virgo: A Preliminary Exploration on Reproducing o1-like MLLM","date":"2025-01-03","arxiv_id":"2501.01904","repositories_listed":2,"syntology":null},{"url":"/paper/distill-visual-chart-reasoning-ability-from","slug":"distill-visual-chart-reasoning-ability-from","title":"Distill Visual Chart Reasoning Ability from LLMs to MLLMs","date":"2024-10-24","arxiv_id":"2410.18798","repositories_listed":2,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":3,"n_honours":4,"n_violates":0,"n_no_contract":3,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/distill-visual-chart-reasoning-ability-from#ran","syntology_url":"https://syntology.ai/paper/2410.18798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18798"}},"official":{"repos":["hewei2001/reachqa"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/from-the-least-to-the-most-building-a-plug","slug":"from-the-least-to-the-most-building-a-plug","title":"From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis","date":"2024-06-28","arxiv_id":"2406.19934","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":11,"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) · 3 unverified","sample_list":"/paper/from-the-least-to-the-most-building-a-plug#ran","syntology_url":"https://syntology.ai/paper/2406.19934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19934"}},"official":{"repos":["steven-ccq/visualreasoner"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/slot-abstractors-toward-scalable-abstract","slug":"slot-abstractors-toward-scalable-abstract","title":"Slot Abstractors: Toward Scalable Abstract Visual Reasoning","date":"2024-03-06","arxiv_id":"2403.03458","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/slot-abstractors-toward-scalable-abstract#ran","syntology_url":"https://syntology.ai/paper/2403.03458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03458"}},"official":{"repos":["shanka123/slot-abstractor","slotabstractor/slotabstractor"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-networks-for-abstraction-and-reasoning","slug":"neural-networks-for-abstraction-and-reasoning","title":"Neural networks for abstraction and reasoning: Towards broad generalization in machines","date":"2024-02-05","arxiv_id":"2402.03507","repositories_listed":2,"syntology":null},{"url":"/paper/a-challenger-to-gpt-4v-early-explorations-of","slug":"a-challenger-to-gpt-4v-early-explorations-of","title":"A Challenger to GPT-4V? Early Explorations of Gemini in Visual Expertise","date":"2023-12-19","arxiv_id":"2312.12436","repositories_listed":2,"syntology":null},{"url":"/paper/benchlmm-benchmarking-cross-style-visual","slug":"benchlmm-benchmarking-cross-style-visual","title":"BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models","date":"2023-12-05","arxiv_id":"2312.02896","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchlmm-benchmarking-cross-style-visual#ran","syntology_url":"https://syntology.ai/paper/2312.02896","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02896"}},"official":{"repos":["aifeg/benchgpt","aifeg/benchlmm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/x-instructblip-a-framework-for-aligning-x","slug":"x-instructblip-a-framework-for-aligning-x","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","date":"2023-11-30","arxiv_id":"2311.18799","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/x-instructblip-a-framework-for-aligning-x#ran","syntology_url":"https://syntology.ai/paper/2311.18799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18799"}},"official":{"repos":["artemisp/lavis-xinstructblip","salesforce/lavis"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mmicl-empowering-vision-language-model-with","slug":"mmicl-empowering-vision-language-model-with","title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","date":"2023-09-14","arxiv_id":"2309.07915","repositories_listed":2,"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":7,"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/mmicl-empowering-vision-language-model-with#ran","syntology_url":"https://syntology.ai/paper/2309.07915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07915"}},"official":{"repos":["haozhezhao/mic","pkunlp-icler/mic"],"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/uni-nlx-unifying-textual-explanations-for","slug":"uni-nlx-unifying-textual-explanations-for","title":"Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks","date":"2023-08-17","arxiv_id":"2308.09033","repositories_listed":2,"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":6,"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/uni-nlx-unifying-textual-explanations-for#ran","syntology_url":"https://syntology.ai/paper/2308.09033","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09033"}},"official":{"repos":["fawazsammani/uni-nlx","fawazsammani/nlxgpt"],"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/measuring-progress-in-fine-grained-vision-and","slug":"measuring-progress-in-fine-grained-vision-and","title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","date":"2023-05-12","arxiv_id":"2305.07558","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/measuring-progress-in-fine-grained-vision-and#ran","syntology_url":"https://syntology.ai/paper/2305.07558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07558"}},"official":{"repos":["e-bug/fine-grained-evals"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/new-benchmarks-for-accountable-text-based","slug":"new-benchmarks-for-accountable-text-based","title":"Accountable Textual-Visual Chat Learns to Reject Human Instructions in Image Re-creation","date":"2023-03-10","arxiv_id":"2303.05983","repositories_listed":2,"syntology":null},{"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/super-clevr-a-virtual-benchmark-to-diagnose","slug":"super-clevr-a-virtual-benchmark-to-diagnose","title":"Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning","date":"2022-12-01","arxiv_id":"2212.00259","repositories_listed":2,"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":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/super-clevr-a-virtual-benchmark-to-diagnose#ran","syntology_url":"https://syntology.ai/paper/2212.00259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.00259"}},"official":{"repos":["lizw14/super-clevr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/x-2-vlm-all-in-one-pre-trained-model-for","slug":"x-2-vlm-all-in-one-pre-trained-model-for","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","date":"2022-11-22","arxiv_id":"2211.12402","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/x-2-vlm-all-in-one-pre-trained-model-for#ran","syntology_url":"https://syntology.ai/paper/2211.12402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12402"}},"official":{"repos":["zengyan-97/x2-vlm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/image-as-a-foreign-language-beit-pretraining","slug":"image-as-a-foreign-language-beit-pretraining","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","date":"2022-08-22","arxiv_id":"2208.10442","repositories_listed":2,"syntology":null},{"url":"/paper/winoground-probing-vision-and-language-models","slug":"winoground-probing-vision-and-language-models","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","date":"2022-04-07","arxiv_id":"2204.03162","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}},"official":null}},{"url":"/paper/dall-eval-probing-the-reasoning-skills-and","slug":"dall-eval-probing-the-reasoning-skills-and","title":"DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models","date":"2022-02-08","arxiv_id":"2202.04053","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dall-eval-probing-the-reasoning-skills-and#ran","syntology_url":"https://syntology.ai/paper/2202.04053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.04053"}},"official":{"repos":["j-min/dalleval"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/raven-s-progressive-matrices-completion-with","slug":"raven-s-progressive-matrices-completion-with","title":"Raven's Progressive Matrices Completion with Latent Gaussian Process Priors","date":"2021-03-22","arxiv_id":"2103.12045","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/structured-multimodal-attentions-for-textvqa","slug":"structured-multimodal-attentions-for-textvqa","title":"Structured Multimodal Attentions for TextVQA","date":"2020-06-01","arxiv_id":"2006.00753","repositories_listed":2,"syntology":null},{"url":"/paper/machine-number-sense-a-dataset-of-visual","slug":"machine-number-sense-a-dataset-of-visual","title":"Machine Number Sense: A Dataset of Visual Arithmetic Problems for Abstract and Relational Reasoning","date":"2020-04-25","arxiv_id":"2004.12193","repositories_listed":2,"syntology":null},{"url":"/paper/smart-home-appliances-chat-with-your-fridge","slug":"smart-home-appliances-chat-with-your-fridge","title":"Smart Home Appliances: Chat with Your Fridge","date":"2019-12-19","arxiv_id":"1912.09589","repositories_listed":2,"syntology":null},{"url":"/paper/visual-semantic-reasoning-for-image-text","slug":"visual-semantic-reasoning-for-image-text","title":"Visual Semantic Reasoning for Image-Text Matching","date":"2019-09-06","arxiv_id":"1909.02701","repositories_listed":2,"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/visual-semantic-reasoning-for-image-text#ran","syntology_url":"https://syntology.ai/paper/1909.02701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02701"}},"official":{"repos":["KunpengLi1994/VSRN"],"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/phyre-a-new-benchmark-for-physical-reasoning","slug":"phyre-a-new-benchmark-for-physical-reasoning","title":"PHYRE: A New Benchmark for Physical Reasoning","date":"2019-08-15","arxiv_id":"1908.05656","repositories_listed":2,"syntology":null},{"url":"/paper/explainable-and-explicit-visual-reasoning","slug":"explainable-and-explicit-visual-reasoning","title":"Explainable and Explicit Visual Reasoning over Scene Graphs","date":"2018-12-05","arxiv_id":"1812.01855","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/explainable-and-explicit-visual-reasoning#ran","syntology_url":"https://syntology.ai/paper/1812.01855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.01855"}},"official":{"repos":["shijx12/XNM-Net"],"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"]}}},{"url":"/paper/a-corpus-for-reasoning-about-natural-language","slug":"a-corpus-for-reasoning-about-natural-language","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","date":"2018-11-01","arxiv_id":"1811.00491","repositories_listed":2,"syntology":null},{"url":"/paper/mapping-natural-language-commands-to-web","slug":"mapping-natural-language-commands-to-web","title":"Mapping Natural Language Commands to Web Elements","date":"2018-08-28","arxiv_id":"1808.09132","repositories_listed":2,"syntology":null},{"url":"/paper/learning-visual-reasoning-without-strong","slug":"learning-visual-reasoning-without-strong","title":"Learning Visual Reasoning Without Strong Priors","date":"2017-07-10","arxiv_id":"1707.03017","repositories_listed":2,"syntology":null},{"url":"/paper/beyond-task-specific-reasoning-a-unified","slug":"beyond-task-specific-reasoning-a-unified","title":"Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning","date":"2025-07-15","arxiv_id":"2507.11761","repositories_listed":1,"syntology":null},{"url":"/paper/orchestrator-agent-trust-a-modular-agentic-ai","slug":"orchestrator-agent-trust-a-modular-agentic-ai","title":"Orchestrator-Agent Trust: A Modular Agentic AI Visual Classification System with Trust-Aware Orchestration and RAG-Based Reasoning","date":"2025-07-09","arxiv_id":"2507.10571","repositories_listed":1,"syntology":null},{"url":"/paper/high-resolution-visual-reasoning-via-multi","slug":"high-resolution-visual-reasoning-via-multi","title":"High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning","date":"2025-07-08","arxiv_id":"2507.05920","repositories_listed":1,"syntology":null},{"url":"/paper/machine-mental-imagery-empower-multimodal","slug":"machine-mental-imagery-empower-multimodal","title":"Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens","date":"2025-06-20","arxiv_id":"2506.17218","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":2,"n_instrument":12,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":17,"phrase":"14 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; 12 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/machine-mental-imagery-empower-multimodal#ran","syntology_url":"https://syntology.ai/paper/2506.17218","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.17218"}},"official":{"repos":["umass-embodied-agi/mirage"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-matters-simple-visual-perturbations","slug":"vision-matters-simple-visual-perturbations","title":"Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning","date":"2025-06-11","arxiv_id":"2506.09736","repositories_listed":1,"syntology":null},{"url":"/paper/vrest-enhancing-reasoning-in-large-vision","slug":"vrest-enhancing-reasoning-in-large-vision","title":"VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism","date":"2025-06-10","arxiv_id":"2506.08691","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":4,"n_instrument":8,"n_unverified":3,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vrest-enhancing-reasoning-in-large-vision#ran","syntology_url":"https://syntology.ai/paper/2506.08691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08691"}},"official":{"repos":["garyjiajia/vrest"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-step-visual-reasoning-with-visual","slug":"multi-step-visual-reasoning-with-visual","title":"Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification","date":"2025-06-08","arxiv_id":"2506.07235","repositories_listed":1,"syntology":null},{"url":"/paper/mint-cot-enabling-interleaved-visual-tokens","slug":"mint-cot-enabling-interleaved-visual-tokens","title":"MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning","date":"2025-06-05","arxiv_id":"2506.05331","repositories_listed":1,"syntology":null},{"url":"/paper/controlthinker-unveiling-latent-semantics-for","slug":"controlthinker-unveiling-latent-semantics-for","title":"ControlThinker: Unveiling Latent Semantics for Controllable Image Generation through Visual Reasoning","date":"2025-06-04","arxiv_id":"2506.03596","repositories_listed":1,"syntology":null},{"url":"/paper/agent-x-evaluating-deep-multimodal-reasoning","slug":"agent-x-evaluating-deep-multimodal-reasoning","title":"Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks","date":"2025-05-30","arxiv_id":"2505.24876","repositories_listed":1,"syntology":null},{"url":"/paper/drvd-bench-do-vision-language-models-reason","slug":"drvd-bench-do-vision-language-models-reason","title":"DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?","date":"2025-05-30","arxiv_id":"2505.24173","repositories_listed":1,"syntology":null},{"url":"/paper/open-captchaworld-a-comprehensive-web-based","slug":"open-captchaworld-a-comprehensive-web-based","title":"Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents","date":"2025-05-30","arxiv_id":"2505.24878","repositories_listed":1,"syntology":null},{"url":"/paper/proxythinker-test-time-guidance-through-small","slug":"proxythinker-test-time-guidance-through-small","title":"ProxyThinker: Test-Time Guidance through Small Visual Reasoners","date":"2025-05-30","arxiv_id":"2505.24872","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcing-video-reasoning-with-focused","slug":"reinforcing-video-reasoning-with-focused","title":"Reinforcing Video Reasoning with Focused Thinking","date":"2025-05-30","arxiv_id":"2505.24718","repositories_listed":1,"syntology":null},{"url":"/paper/seeing-is-not-reasoning-mvpbench-for-graph","slug":"seeing-is-not-reasoning-mvpbench-for-graph","title":"Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT","date":"2025-05-30","arxiv_id":"2505.24182","repositories_listed":1,"syntology":null},{"url":"/paper/grounded-reinforcement-learning-for-visual","slug":"grounded-reinforcement-learning-for-visual","title":"Grounded Reinforcement Learning for Visual Reasoning","date":"2025-05-29","arxiv_id":"2505.23678","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-perception-evaluating-abstract-visual","slug":"beyond-perception-evaluating-abstract-visual","title":"Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task","date":"2025-05-28","arxiv_id":"2505.21850","repositories_listed":1,"syntology":null},{"url":"/paper/understand-think-and-answer-advancing-visual","slug":"understand-think-and-answer-advancing-visual","title":"Understand, Think, and Answer: Advancing Visual Reasoning with Large Multimodal Models","date":"2025-05-27","arxiv_id":"2505.20753","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":1,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/understand-think-and-answer-advancing-visual#ran","syntology_url":"https://syntology.ai/paper/2505.20753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20753"}},"official":{"repos":["jefferyzhan/griffon"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-abstract-thinking-empowers-multimodal","slug":"visual-abstract-thinking-empowers-multimodal","title":"Visual Abstract Thinking Empowers Multimodal Reasoning","date":"2025-05-26","arxiv_id":"2505.20164","repositories_listed":1,"syntology":null},{"url":"/paper/are-vision-language-models-ready-for-clinical","slug":"are-vision-language-models-ready-for-clinical","title":"Are Vision Language Models Ready for Clinical Diagnosis? A 3D Medical Benchmark for Tumor-centric Visual Question Answering","date":"2025-05-25","arxiv_id":"2505.18915","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/are-vision-language-models-ready-for-clinical#ran","syntology_url":"https://syntology.ai/paper/2505.18915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18915"}},"official":{"repos":["schuture/deeptumorvqa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/chartsketcher-reasoning-with-multimodal","slug":"chartsketcher-reasoning-with-multimodal","title":"ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding","date":"2025-05-25","arxiv_id":"2505.19076","repositories_listed":1,"syntology":null},{"url":"/paper/seephys-does-seeing-help-thinking","slug":"seephys-does-seeing-help-thinking","title":"SeePhys: Does Seeing Help Thinking? -- Benchmarking Vision-Based Physics Reasoning","date":"2025-05-25","arxiv_id":"2505.19099","repositories_listed":1,"syntology":null},{"url":"/paper/vtool-r1-vlms-learn-to-think-with-images-via","slug":"vtool-r1-vlms-learn-to-think-with-images-via","title":"VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use","date":"2025-05-25","arxiv_id":"2505.19255","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/vtool-r1-vlms-learn-to-think-with-images-via#ran","syntology_url":"https://syntology.ai/paper/2505.19255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19255"}},"official":null}},{"url":"/paper/gre-suite-geo-localization-inference-via-fine","slug":"gre-suite-geo-localization-inference-via-fine","title":"GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains","date":"2025-05-24","arxiv_id":"2505.18700","repositories_listed":1,"syntology":null},{"url":"/paper/daily-omni-towards-audio-visual-reasoning","slug":"daily-omni-towards-audio-visual-reasoning","title":"Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities","date":"2025-05-23","arxiv_id":"2505.17862","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/daily-omni-towards-audio-visual-reasoning#ran","syntology_url":"https://syntology.ai/paper/2505.17862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17862"}},"official":{"repos":["lliar-liar/daily-omni"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/danmakutppbench-a-multi-modal-benchmark-for","slug":"danmakutppbench-a-multi-modal-benchmark-for","title":"DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understanding","date":"2025-05-23","arxiv_id":"2505.18411","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/danmakutppbench-a-multi-modal-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2505.18411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18411"}},"official":{"repos":["frenkie-chiang/danmakutppbench"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/arb-a-comprehensive-arabic-multimodal","slug":"arb-a-comprehensive-arabic-multimodal","title":"ARB: A Comprehensive Arabic Multimodal Reasoning Benchmark","date":"2025-05-22","arxiv_id":"2505.17021","repositories_listed":1,"syntology":null},{"url":"/paper/lavida-a-large-diffusion-language-model-for","slug":"lavida-a-large-diffusion-language-model-for","title":"LaViDa: A Large Diffusion Language Model for Multimodal Understanding","date":"2025-05-22","arxiv_id":"2505.16839","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 5 unverified","sample_list":"/paper/lavida-a-large-diffusion-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2505.16839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16839"}},"official":{"repos":["jacklishufan/lavida"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/openseg-r-improving-open-vocabulary","slug":"openseg-r-improving-open-vocabulary","title":"OpenSeg-R: Improving Open-Vocabulary Segmentation via Step-by-Step Visual Reasoning","date":"2025-05-22","arxiv_id":"2505.16974","repositories_listed":1,"syntology":null}],"syntology_records":57,"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":3,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/visual-reasoning-on-vsr","since_archive":"/sota/visual-reasoning-on-vsr#since-judged","papers_judged":3,"placed":0}]},"papers_where_code_ran":165,"papers_where_code_ran_first_page":"/task/visual-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":"archive","page":2,"of":7,"url":"/task/visual-reasoning/papers/2","json":"/task/visual-reasoning/papers/2.json","rows":100},{"order":"archive","page":3,"of":7,"url":"/task/visual-reasoning/papers/3","json":"/task/visual-reasoning/papers/3.json","rows":100},{"order":"archive","page":4,"of":7,"url":"/task/visual-reasoning/papers/4","json":"/task/visual-reasoning/papers/4.json","rows":100},{"order":"archive","page":5,"of":7,"url":"/task/visual-reasoning/papers/5","json":"/task/visual-reasoning/papers/5.json","rows":100},{"order":"archive","page":6,"of":7,"url":"/task/visual-reasoning/papers/6","json":"/task/visual-reasoning/papers/6.json","rows":100},{"order":"archive","page":7,"of":7,"url":"/task/visual-reasoning/papers/7","json":"/task/visual-reasoning/papers/7.json","rows":98},{"order":"ran","page":1,"of":2,"url":"/task/visual-reasoning/papers/ran/1","json":"/task/visual-reasoning/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/visual-reasoning/papers/ran/2","json":"/task/visual-reasoning/papers/ran/2.json","rows":65}],"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":"7a746f353e56202d65f4c4e0e20b005427a777fb4a2637704d63013e1c039c6a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}