{"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/multimodal-reasoning","name":"Multimodal Reasoning","slug":"multimodal-reasoning","description_markdown":"Reasoning over multimodal inputs.","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":302,"papers_with_code":138,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":11,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/multimodal-reasoning-on-rebus","slug":"multimodal-reasoning-on-rebus","dataset":"REBUS","dataset_url":"/dataset/rebus","rows_in_archive":8,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GPT-4V","paper_title":"REBUS: A Robust Evaluation Benchmark of Understanding Symbols","paper_url":"/paper/rebus-a-robust-evaluation-benchmark-of-1","paper_date":"2024-01-11","arxiv_id":"2401.05604","code_links":[{"title":"cvndsh/rebus","url":"https://github.com/cvndsh/rebus"}],"syntology":null}},{"leaderboard":"/sota/multimodal-reasoning-on-math-v","slug":"multimodal-reasoning-on-math-v","dataset":"MATH-V","dataset_url":"/dataset/math-v","rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GPT4V","paper_title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","paper_url":"/paper/measuring-multimodal-mathematical-reasoning","paper_date":"2024-02-22","arxiv_id":"2402.14804","code_links":[{"title":"mathllm/math-v","url":"https://github.com/mathllm/math-v"}],"syntology":null}},{"leaderboard":"/sota/multimodal-reasoning-on-algopuzzlevqa","slug":"multimodal-reasoning-on-algopuzzlevqa","dataset":"AlgoPuzzleVQA","dataset_url":"/dataset/algopuzzlevqa","rows_in_archive":1,"metrics":["Acc"],"first_row_in_archive_order":{"model":"GPT-4","paper_title":"Are Language Models Puzzle Prodigies? Algorithmic Puzzles Unveil Serious Challenges in Multimodal Reasoning","paper_url":"/paper/are-language-models-puzzle-prodigies","paper_date":"2024-03-06","arxiv_id":"2403.03864","code_links":[{"title":"declare-lab/puzzle-reasoning","url":"https://github.com/declare-lab/puzzle-reasoning"},{"title":"declare-lab/llm-puzzletest","url":"https://github.com/declare-lab/llm-puzzletest"}],"syntology":null}}],"datasets":[{"url":"/dataset/meetingbank","name":"MeetingBank","full_name":"","num_papers_in_archive":16},{"url":"/dataset/math-v","name":"MATH-V","full_name":"","num_papers_in_archive":12},{"url":"/dataset/vl-rewardbench","name":"VL-RewardBench","full_name":"","num_papers_in_archive":8},{"url":"/dataset/m3gia","name":"M3GIA","full_name":"","num_papers_in_archive":5},{"url":"/dataset/algopuzzlevqa","name":"AlgoPuzzleVQA","full_name":"","num_papers_in_archive":1},{"url":"/dataset/emma","name":"EMMA","full_name":"An Enhanced MultiModal ReAsoning Benchmark","num_papers_in_archive":1},{"url":"/dataset/gameqa","name":"GameQA","full_name":"GameQA-140K","num_papers_in_archive":1},{"url":"/dataset/polymath","name":"PolyMATH","full_name":"","num_papers_in_archive":1},{"url":"/dataset/r1-onevision","name":"R1-Onevision","full_name":"","num_papers_in_archive":1},{"url":"/dataset/rebus","name":"REBUS","full_name":"A Robust Evaluation Benchmark of Understanding Symbols","num_papers_in_archive":1},{"url":"/dataset/taste-music-dataset","name":"taste-music-dataset","full_name":"Taste Music Dataset","num_papers_in_archive":1}],"subtasks":[{"url":"/task/mme","name":"MME"}],"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":4,"rows_per_page":100,"shown":100,"of":302,"of_with_code":138,"tagged_in_all":302,"counts":{"archive_papers_tagged":302,"with_a_code_link":138,"where_syntology_ran_a_sample":52,"not_listed_spam_title":0,"listed":302,"listed_where_code_ran":52,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":43,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":43,"listed_every_run_a_failure_of_syntologys_instrument":9,"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/chartgalaxy-a-dataset-for-infographic-chart","slug":"chartgalaxy-a-dataset-for-infographic-chart","title":"ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation","date":"2025-05-24","arxiv_id":"2505.18668","repositories_listed":3,"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":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/chartgalaxy-a-dataset-for-infographic-chart#ran","syntology_url":"https://syntology.ai/paper/2505.18668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18668"}},"official":{"repos":["chartgalaxy/chartgalaxy"],"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/webqa-multihop-and-multimodal-qa","slug":"webqa-multihop-and-multimodal-qa","title":"WebQA: Multihop and Multimodal QA","date":"2021-09-01","arxiv_id":"2109.00590","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/webqa-multihop-and-multimodal-qa#ran","syntology_url":"https://syntology.ai/paper/2109.00590","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00590"}},"official":null}},{"url":"/paper/e-snli-ve-2-0-corrected-visual-textual","slug":"e-snli-ve-2-0-corrected-visual-textual","title":"e-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations","date":"2020-04-07","arxiv_id":"2004.03744","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/e-snli-ve-2-0-corrected-visual-textual#ran","syntology_url":"https://syntology.ai/paper/2004.03744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.03744"}},"official":{"repos":["virginie-do/e-SNLI-VE"],"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/advancing-multimodal-reasoning-via","slug":"advancing-multimodal-reasoning-via","title":"Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start","date":"2025-05-28","arxiv_id":"2505.22334","repositories_listed":2,"syntology":null},{"url":"/paper/emerging-properties-in-unified-multimodal","slug":"emerging-properties-in-unified-multimodal","title":"Emerging Properties in Unified Multimodal Pretraining","date":"2025-05-20","arxiv_id":"2505.14683","repositories_listed":2,"syntology":{"n":21,"n_ran":19,"n_constructed":0,"n_ran_checked":14,"n_instrument":5,"n_unverified":2,"n_honours":4,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 4 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/emerging-properties-in-unified-multimodal#ran","syntology_url":"https://syntology.ai/paper/2505.14683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14683"}},"official":null}},{"url":"/paper/mm-prm-enhancing-multimodal-mathematical","slug":"mm-prm-enhancing-multimodal-mathematical","title":"MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision","date":"2025-05-19","arxiv_id":"2505.13427","repositories_listed":2,"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":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mm-prm-enhancing-multimodal-mathematical#ran","syntology_url":"https://syntology.ai/paper/2505.13427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13427"}},"official":{"repos":["modalminds/mm-prm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sakura-on-the-multi-hop-reasoning-of-large","slug":"sakura-on-the-multi-hop-reasoning-of-large","title":"SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information","date":"2025-05-19","arxiv_id":"2505.13237","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/sakura-on-the-multi-hop-reasoning-of-large#ran","syntology_url":"https://syntology.ai/paper/2505.13237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13237"}},"official":{"repos":["b08202033/SAKURA","ckyang1124/sakura"],"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/vl-rethinker-incentivizing-self-reflection-of","slug":"vl-rethinker-incentivizing-self-reflection-of","title":"VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning","date":"2025-04-10","arxiv_id":"2504.08837","repositories_listed":2,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/vl-rethinker-incentivizing-self-reflection-of#ran","syntology_url":"https://syntology.ai/paper/2504.08837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.08837"}},"official":null}},{"url":"/paper/the-jumping-reasoning-curve-tracking-the","slug":"the-jumping-reasoning-curve-tracking-the","title":"The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles","date":"2025-02-03","arxiv_id":"2502.01081","repositories_listed":2,"syntology":null},{"url":"/paper/llava-o1-let-vision-language-models-reason","slug":"llava-o1-let-vision-language-models-reason","title":"LLaVA-CoT: Let Vision Language Models Reason Step-by-Step","date":"2024-11-15","arxiv_id":"2411.10440","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llava-o1-let-vision-language-models-reason#ran","syntology_url":"https://syntology.ai/paper/2411.10440","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10440"}},"official":{"repos":["PKU-YuanGroup/LLaVA-CoT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/2408-01337","slug":"2408-01337","title":"MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models","date":"2024-08-02","arxiv_id":"2408.01337","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":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/2408-01337#ran","syntology_url":"https://syntology.ai/paper/2408.01337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01337"}},"official":{"repos":["mulab-mir/muchomusic"],"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/puzzlevqa-diagnosing-multimodal-reasoning","slug":"puzzlevqa-diagnosing-multimodal-reasoning","title":"PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns","date":"2024-03-20","arxiv_id":"2403.13315","repositories_listed":2,"syntology":{"n":14,"n_ran":14,"n_constructed":0,"n_ran_checked":7,"n_instrument":7,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/puzzlevqa-diagnosing-multimodal-reasoning#ran","syntology_url":"https://syntology.ai/paper/2403.13315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13315"}},"official":{"repos":["declare-lab/llm-puzzletest"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/are-language-models-puzzle-prodigies","slug":"are-language-models-puzzle-prodigies","title":"Are Language Models Puzzle Prodigies? Algorithmic Puzzles Unveil Serious Challenges in Multimodal Reasoning","date":"2024-03-06","arxiv_id":"2403.03864","repositories_listed":2,"syntology":null},{"url":"/paper/mm-bigbench-evaluating-multimodal-models-on","slug":"mm-bigbench-evaluating-multimodal-models-on","title":"MM-BigBench: Evaluating Multimodal Models on Multimodal Content Comprehension Tasks","date":"2023-10-13","arxiv_id":"2310.09036","repositories_listed":2,"syntology":null},{"url":"/paper/beyond-chain-of-thought-effective-graph-of","slug":"beyond-chain-of-thought-effective-graph-of","title":"Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models","date":"2023-05-26","arxiv_id":"2305.16582","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/beyond-chain-of-thought-effective-graph-of#ran","syntology_url":"https://syntology.ai/paper/2305.16582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16582"}},"official":{"repos":["zoeyyao27/graph-of-thought"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-analogical-reasoning-over","slug":"multimodal-analogical-reasoning-over","title":"Multimodal Analogical Reasoning over Knowledge Graphs","date":"2022-10-01","arxiv_id":"2210.00312","repositories_listed":2,"syntology":{"n":27,"n_ran":17,"n_constructed":2,"n_ran_checked":14,"n_instrument":3,"n_unverified":10,"n_honours":1,"n_violates":1,"n_no_contract":12,"n_pointer_only":2,"phrase":"17 ran (of which 2 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/multimodal-analogical-reasoning-over#ran","syntology_url":"https://syntology.ai/paper/2210.00312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.00312"}},"official":{"repos":["zjunlp/MKG_Analogy"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":10,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/dual-attention-networks-for-multimodal","slug":"dual-attention-networks-for-multimodal","title":"Dual Attention Networks for Multimodal Reasoning and Matching","date":"2016-11-02","arxiv_id":"1611.00471","repositories_listed":2,"syntology":null},{"url":"/paper/dreamvla-a-vision-language-action-model-1","slug":"dreamvla-a-vision-language-action-model-1","title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","date":"2025-07-06","arxiv_id":"2507.04447","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dreamvla-a-vision-language-action-model-1#ran","syntology_url":"https://syntology.ai/paper/2507.04447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.04447"}},"official":{"repos":["Zhangwenyao1/DreamVLA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/glm-4-1v-thinking-towards-versatile","slug":"glm-4-1v-thinking-towards-versatile","title":"GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning","date":"2025-07-01","arxiv_id":"2507.01006","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":1,"n_instrument":10,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"11 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; 10 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glm-4-1v-thinking-towards-versatile#ran","syntology_url":"https://syntology.ai/paper/2507.01006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.01006"}},"official":{"repos":["thudm/glm-4.1v-thinking"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/thinking-with-images-for-multimodal-reasoning","slug":"thinking-with-images-for-multimodal-reasoning","title":"Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers","date":"2025-06-30","arxiv_id":"2506.23918","repositories_listed":1,"syntology":null},{"url":"/paper/humanomniv2-from-understanding-to-omni-modal","slug":"humanomniv2-from-understanding-to-omni-modal","title":"HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context","date":"2025-06-26","arxiv_id":"2506.21277","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/metis-rise-rl-incentivizes-and-sft-enhances","slug":"metis-rise-rl-incentivizes-and-sft-enhances","title":"Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model Learning","date":"2025-06-16","arxiv_id":"2506.13056","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcing-spatial-reasoning-in-vision","slug":"reinforcing-spatial-reasoning-in-vision","title":"Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing","date":"2025-06-11","arxiv_id":"2506.09965","repositories_listed":1,"syntology":null},{"url":"/paper/play-to-generalize-learning-to-reason-through","slug":"play-to-generalize-learning-to-reason-through","title":"Play to Generalize: Learning to Reason Through Game Play","date":"2025-06-09","arxiv_id":"2506.08011","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/play-to-generalize-learning-to-reason-through#ran","syntology_url":"https://syntology.ai/paper/2506.08011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08011"}},"official":{"repos":["yunfeixie233/vigal"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/wethink-toward-general-purpose-vision","slug":"wethink-toward-general-purpose-vision","title":"WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning","date":"2025-06-09","arxiv_id":"2506.07905","repositories_listed":1,"syntology":null},{"url":"/paper/learning-compact-vision-tokens-for-efficient","slug":"learning-compact-vision-tokens-for-efficient","title":"Learning Compact Vision Tokens for Efficient Large Multimodal Models","date":"2025-06-08","arxiv_id":"2506.07138","repositories_listed":1,"syntology":null},{"url":"/paper/morse-500-a-programmatically-controllable","slug":"morse-500-a-programmatically-controllable","title":"MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning","date":"2025-06-05","arxiv_id":"2506.05523","repositories_listed":1,"syntology":null},{"url":"/paper/mimo-vl-technical-report","slug":"mimo-vl-technical-report","title":"MiMo-VL Technical Report","date":"2025-06-04","arxiv_id":"2506.03569","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mimo-vl-technical-report#ran","syntology_url":"https://syntology.ai/paper/2506.03569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.03569"}},"official":{"repos":["xiaomimimo/mimo-vl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/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/mmboundary-advancing-mllm-knowledge-boundary","slug":"mmboundary-advancing-mllm-knowledge-boundary","title":"MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence Calibration","date":"2025-05-29","arxiv_id":"2505.23224","repositories_listed":1,"syntology":null},{"url":"/paper/vidtext-towards-comprehensive-evaluation-for","slug":"vidtext-towards-comprehensive-evaluation-for","title":"VidText: Towards Comprehensive Evaluation for Video Text Understanding","date":"2025-05-28","arxiv_id":"2505.22810","repositories_listed":1,"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":2,"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/vidtext-towards-comprehensive-evaluation-for#ran","syntology_url":"https://syntology.ai/paper/2505.22810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.22810"}},"official":{"repos":["shuyansy/vidtext"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/video-holmes-can-mllm-think-like-holmes-for","slug":"video-holmes-can-mllm-think-like-holmes-for","title":"Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?","date":"2025-05-27","arxiv_id":"2505.21374","repositories_listed":1,"syntology":null},{"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/satori-r1-incentivizing-multimodal-reasoning","slug":"satori-r1-incentivizing-multimodal-reasoning","title":"SATORI-R1: Incentivizing Multimodal Reasoning with Spatial Grounding and Verifiable Rewards","date":"2025-05-25","arxiv_id":"2505.19094","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/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/code2logic-game-code-driven-data-synthesis","slug":"code2logic-game-code-driven-data-synthesis","title":"Code2Logic: Game-Code-Driven Data Synthesis for Enhancing VLMs General Reasoning","date":"2025-05-20","arxiv_id":"2505.13886","repositories_listed":1,"syntology":{"n":15,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/code2logic-game-code-driven-data-synthesis#ran","syntology_url":"https://syntology.ai/paper/2505.13886","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13886"}},"official":{"repos":["tongjingqi/code2logic"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deepeyes-incentivizing-thinking-with-images","slug":"deepeyes-incentivizing-thinking-with-images","title":"DeepEyes: Incentivizing \"Thinking with Images\" via Reinforcement Learning","date":"2025-05-20","arxiv_id":"2505.14362","repositories_listed":1,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":4,"phrase":"12 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; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/deepeyes-incentivizing-thinking-with-images#ran","syntology_url":"https://syntology.ai/paper/2505.14362","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14362"}},"official":{"repos":["visual-agent/deepeyes"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/kgalign-joint-semantic-structural-knowledge","slug":"kgalign-joint-semantic-structural-knowledge","title":"KGAlign: Joint Semantic-Structural Knowledge Encoding for Multimodal Fake News Detection","date":"2025-05-18","arxiv_id":"2505.14714","repositories_listed":1,"syntology":null},{"url":"/paper/logicocr-do-your-large-multimodal-models","slug":"logicocr-do-your-large-multimodal-models","title":"LogicOCR: Do Your Large Multimodal Models Excel at Logical Reasoning on Text-Rich Images?","date":"2025-05-18","arxiv_id":"2505.12307","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11404","slug":"2505-11404","title":"Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner","date":"2025-05-16","arxiv_id":"2505.11404","repositories_listed":1,"syntology":null},{"url":"/paper/perception-reason-think-and-plan-a-survey-on","slug":"perception-reason-think-and-plan-a-survey-on","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","date":"2025-05-08","arxiv_id":"2505.04921","repositories_listed":1,"syntology":null},{"url":"/paper/videomultiagents-a-multi-agent-framework-for","slug":"videomultiagents-a-multi-agent-framework-for","title":"VideoMultiAgents: A Multi-Agent Framework for Video Question Answering","date":"2025-04-25","arxiv_id":"2504.20091","repositories_listed":1,"syntology":null},{"url":"/paper/skywork-r1v2-multimodal-hybrid-reinforcement","slug":"skywork-r1v2-multimodal-hybrid-reinforcement","title":"Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning","date":"2025-04-23","arxiv_id":"2504.16656","repositories_listed":1,"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/skywork-r1v2-multimodal-hybrid-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2504.16656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.16656"}},"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":["official"]}}},{"url":"/paper/embodied-r-collaborative-framework-for","slug":"embodied-r-collaborative-framework-for","title":"Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning","date":"2025-04-17","arxiv_id":"2504.12680","repositories_listed":1,"syntology":null},{"url":"/paper/breaking-the-data-barrier-building-gui-agents","slug":"breaking-the-data-barrier-building-gui-agents","title":"Breaking the Data Barrier -- Building GUI Agents Through Task Generalization","date":"2025-04-14","arxiv_id":"2504.10127","repositories_listed":1,"syntology":null},{"url":"/paper/hm-rag-hierarchical-multi-agent-multimodal","slug":"hm-rag-hierarchical-multi-agent-multimodal","title":"HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation","date":"2025-04-13","arxiv_id":"2504.12330","repositories_listed":1,"syntology":null},{"url":"/paper/kimi-vl-technical-report","slug":"kimi-vl-technical-report","title":"Kimi-VL Technical Report","date":"2025-04-10","arxiv_id":"2504.07491","repositories_listed":1,"syntology":null},{"url":"/paper/mdk12-bench-a-multi-discipline-benchmark-for-1","slug":"mdk12-bench-a-multi-discipline-benchmark-for-1","title":"MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models","date":"2025-04-08","arxiv_id":"2504.05782","repositories_listed":1,"syntology":null},{"url":"/paper/skywork-r1v-pioneering-multimodal-reasoning","slug":"skywork-r1v-pioneering-multimodal-reasoning","title":"Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought","date":"2025-04-08","arxiv_id":"2504.05599","repositories_listed":1,"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":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/skywork-r1v-pioneering-multimodal-reasoning#ran","syntology_url":"https://syntology.ai/paper/2504.05599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.05599"}},"official":null}},{"url":"/paper/affordable-ai-assistants-with-knowledge-graph","slug":"affordable-ai-assistants-with-knowledge-graph","title":"Affordable AI Assistants with Knowledge Graph of Thoughts","date":"2025-04-03","arxiv_id":"2504.02670","repositories_listed":1,"syntology":null},{"url":"/paper/fortisavqa-and-maven-a-benchmark-dataset-and","slug":"fortisavqa-and-maven-a-benchmark-dataset-and","title":"FortisAVQA and MAVEN: a Benchmark Dataset and Debiasing Framework for Robust Multimodal Reasoning","date":"2025-04-01","arxiv_id":"2504.00487","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-mllm-reasoning-with-text-debiased","slug":"boosting-mllm-reasoning-with-text-debiased","title":"Boosting MLLM Reasoning with Text-Debiased Hint-GRPO","date":"2025-03-31","arxiv_id":"2503.23905","repositories_listed":1,"syntology":null},{"url":"/paper/3mdbench-medical-multimodal-multi-agent","slug":"3mdbench-medical-multimodal-multi-agent","title":"3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark","date":"2025-03-26","arxiv_id":"2504.13861","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/3mdbench-medical-multimodal-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2504.13861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.13861"}},"official":{"repos":["univanxx/3mdbench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/openvlthinker-an-early-exploration-to-complex","slug":"openvlthinker-an-early-exploration-to-complex","title":"OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement","date":"2025-03-21","arxiv_id":"2503.17352","repositories_listed":1,"syntology":{"n":21,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":12,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/openvlthinker-an-early-exploration-to-complex#ran","syntology_url":"https://syntology.ai/paper/2503.17352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.17352"}},"official":{"repos":["yihedeng9/openvlthinker"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":12,"ran_from_kinds":["official"]}}},{"url":"/paper/llava-more-a-comparative-study-of-llms-and","slug":"llava-more-a-comparative-study-of-llms-and","title":"LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning","date":"2025-03-19","arxiv_id":"2503.15621","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":3,"n_no_contract":2,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 3 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/llava-more-a-comparative-study-of-llms-and#ran","syntology_url":"https://syntology.ai/paper/2503.15621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.15621"}},"official":{"repos":["aimagelab/LLaVA-MORE"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/deepperception-advancing-r1-like-cognitive","slug":"deepperception-advancing-r1-like-cognitive","title":"DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding","date":"2025-03-17","arxiv_id":"2503.12797","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deepperception-advancing-r1-like-cognitive#ran","syntology_url":"https://syntology.ai/paper/2503.12797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.12797"}},"official":{"repos":["thunlp/deepperception"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/microvqa-a-multimodal-reasoning-benchmark-for","slug":"microvqa-a-multimodal-reasoning-benchmark-for","title":"MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research","date":"2025-03-17","arxiv_id":"2503.13399","repositories_listed":1,"syntology":null},{"url":"/paper/towards-self-improving-systematic-cognition","slug":"towards-self-improving-systematic-cognition","title":"Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition","date":"2025-03-16","arxiv_id":"2503.12303","repositories_listed":1,"syntology":null},{"url":"/paper/how-do-multimodal-large-language-models","slug":"how-do-multimodal-large-language-models","title":"How Do Multimodal Large Language Models Handle Complex Multimodal Reasoning? Placing Them in An Extensible Escape Game","date":"2025-03-13","arxiv_id":"2503.10042","repositories_listed":1,"syntology":null},{"url":"/paper/r1-onevision-advancing-generalized-multimodal","slug":"r1-onevision-advancing-generalized-multimodal","title":"R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization","date":"2025-03-13","arxiv_id":"2503.10615","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/r1-onevision-advancing-generalized-multimodal#ran","syntology_url":"https://syntology.ai/paper/2503.10615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.10615"}},"official":{"repos":["Fancy-MLLM/R1-onevision"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mindgym-enhancing-vision-language-models-via","slug":"mindgym-enhancing-vision-language-models-via","title":"MindGYM: Enhancing Vision-Language Models via Synthetic Self-Challenging Questions","date":"2025-03-12","arxiv_id":"2503.09499","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":2,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 2 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/mindgym-enhancing-vision-language-models-via#ran","syntology_url":"https://syntology.ai/paper/2503.09499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09499"}},"official":{"repos":["modelscope/data-juicer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/oasis-one-image-is-all-you-need-for","slug":"oasis-one-image-is-all-you-need-for","title":"Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis","date":"2025-03-11","arxiv_id":"2503.08741","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/oasis-one-image-is-all-you-need-for#ran","syntology_url":"https://syntology.ai/paper/2503.08741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08741"}},"official":{"repos":["Letian2003/MM_INF"],"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/lmm-r1-empowering-3b-lmms-with-strong","slug":"lmm-r1-empowering-3b-lmms-with-strong","title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","date":"2025-03-10","arxiv_id":"2503.07536","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/lmm-r1-empowering-3b-lmms-with-strong#ran","syntology_url":"https://syntology.ai/paper/2503.07536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07536"}},"official":null}},{"url":"/paper/mm-eureka-exploring-visual-aha-moment-with","slug":"mm-eureka-exploring-visual-aha-moment-with","title":"MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning","date":"2025-03-10","arxiv_id":"2503.07365","repositories_listed":1,"syntology":null},{"url":"/paper/vision-r1-incentivizing-reasoning-capability","slug":"vision-r1-incentivizing-reasoning-capability","title":"Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models","date":"2025-03-09","arxiv_id":"2503.06749","repositories_listed":1,"syntology":null},{"url":"/paper/can-atomic-step-decomposition-enhance-the","slug":"can-atomic-step-decomposition-enhance-the","title":"Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?","date":"2025-03-08","arxiv_id":"2503.06252","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/can-atomic-step-decomposition-enhance-the#ran","syntology_url":"https://syntology.ai/paper/2503.06252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06252"}},"official":{"repos":["quinn777/atomthink"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/r1-zero-s-aha-moment-in-visual-reasoning-on-a","slug":"r1-zero-s-aha-moment-in-visual-reasoning-on-a","title":"R1-Zero's \"Aha Moment\" in Visual Reasoning on a 2B Non-SFT Model","date":"2025-03-07","arxiv_id":"2503.05132","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/r1-zero-s-aha-moment-in-visual-reasoning-on-a#ran","syntology_url":"https://syntology.ai/paper/2503.05132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.05132"}},"official":{"repos":["turningpoint-ai/visualthinker-r1-zero"],"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","unlocated"]}}},{"url":"/paper/question-aware-gaussian-experts-for-audio","slug":"question-aware-gaussian-experts-for-audio","title":"Question-Aware Gaussian Experts for Audio-Visual Question Answering","date":"2025-03-06","arxiv_id":"2503.04459","repositories_listed":1,"syntology":null},{"url":"/paper/audio-reasoner-improving-reasoning-capability","slug":"audio-reasoner-improving-reasoning-capability","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","date":"2025-03-04","arxiv_id":"2503.02318","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/audio-reasoner-improving-reasoning-capability#ran","syntology_url":"https://syntology.ai/paper/2503.02318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.02318"}},"official":null}},{"url":"/paper/r1-onevision-an-open-source-multimodal-large","slug":"r1-onevision-an-open-source-multimodal-large","title":"R1-Onevision：An Open-Source Multimodal Large Language Model Capable of Deep Reasoning","date":"2025-02-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mm-verify-enhancing-multimodal-reasoning-with","slug":"mm-verify-enhancing-multimodal-reasoning-with","title":"MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification","date":"2025-02-19","arxiv_id":"2502.13383","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"0 ran · 4 unverified","sample_list":"/paper/mm-verify-enhancing-multimodal-reasoning-with#ran","syntology_url":"https://syntology.ai/paper/2502.13383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13383"}},"official":{"repos":["aurora-slz/mm-verify"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/segsub-evaluating-robustness-to-knowledge","slug":"segsub-evaluating-robustness-to-knowledge","title":"SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models","date":"2025-02-19","arxiv_id":"2502.14908","repositories_listed":1,"syntology":null},{"url":"/paper/code-vision-evaluating-multimodal-llms-logic","slug":"code-vision-evaluating-multimodal-llms-logic","title":"Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities","date":"2025-02-17","arxiv_id":"2502.11829","repositories_listed":1,"syntology":null},{"url":"/paper/language-models-can-see-better-visual","slug":"language-models-can-see-better-visual","title":"Language Models Can See Better: Visual Contrastive Decoding For LLM Multimodal Reasoning","date":"2025-02-17","arxiv_id":"2502.11751","repositories_listed":1,"syntology":null},{"url":"/paper/user-vlm-360-personalized-vision-language","slug":"user-vlm-360-personalized-vision-language","title":"USER-VLM 360: Personalized Vision Language Models with User-aware Tuning for Social Human-Robot Interactions","date":"2025-02-15","arxiv_id":"2502.10636","repositories_listed":1,"syntology":null},{"url":"/paper/ask-in-any-modality-a-comprehensive-survey-on","slug":"ask-in-any-modality-a-comprehensive-survey-on","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation","date":"2025-02-12","arxiv_id":"2502.08826","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-reasoning-with-hidden-thinking","slug":"efficient-reasoning-with-hidden-thinking","title":"Efficient Reasoning with Hidden Thinking","date":"2025-01-31","arxiv_id":"2501.19201","repositories_listed":1,"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/efficient-reasoning-with-hidden-thinking#ran","syntology_url":"https://syntology.ai/paper/2501.19201","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.19201"}},"official":{"repos":["shawnricecake/heima"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/socratic-questioning-learn-to-self-guide","slug":"socratic-questioning-learn-to-self-guide","title":"Socratic Questioning: Learn to Self-guide Multimodal Reasoning in the Wild","date":"2025-01-06","arxiv_id":"2501.02964","repositories_listed":1,"syntology":null},{"url":"/paper/linin-logic-integrated-neural-inference","slug":"linin-logic-integrated-neural-inference","title":"LININ: Logic Integrated Neural Inference Network for Explanatory Visual Question Answering","date":"2024-12-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/silvar-speech-driven-multimodal-model-for","slug":"silvar-speech-driven-multimodal-model-for","title":"SilVar: Speech Driven Multimodal Model for Reasoning Visual Question Answering and Object Localization","date":"2024-12-21","arxiv_id":"2412.16771","repositories_listed":1,"syntology":null},{"url":"/paper/do-language-models-understand-time","slug":"do-language-models-understand-time","title":"Do Language Models Understand Time?","date":"2024-12-18","arxiv_id":"2412.13845","repositories_listed":1,"syntology":null},{"url":"/paper/comt-a-novel-benchmark-for-chain-of-multi","slug":"comt-a-novel-benchmark-for-chain-of-multi","title":"CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models","date":"2024-12-17","arxiv_id":"2412.12932","repositories_listed":1,"syntology":null},{"url":"/paper/neptune-the-long-orbit-to-benchmarking-long","slug":"neptune-the-long-orbit-to-benchmarking-long","title":"Neptune: The Long Orbit to Benchmarking Long Video Understanding","date":"2024-12-12","arxiv_id":"2412.09582","repositories_listed":1,"syntology":null},{"url":"/paper/mammoth-vl-eliciting-multimodal-reasoning","slug":"mammoth-vl-eliciting-multimodal-reasoning","title":"MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale","date":"2024-12-06","arxiv_id":"2412.05237","repositories_listed":1,"syntology":null},{"url":"/paper/aguvis-unified-pure-vision-agents-for","slug":"aguvis-unified-pure-vision-agents-for","title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","date":"2024-12-05","arxiv_id":"2412.04454","repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-multimodal-large-language-models","slug":"accelerating-multimodal-large-language-models","title":"Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings","date":"2024-11-29","arxiv_id":"2411.19628","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-the-reasoning-ability-of-multimodal","slug":"enhancing-the-reasoning-ability-of-multimodal","title":"Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization","date":"2024-11-15","arxiv_id":"2411.10442","repositories_listed":1,"syntology":null},{"url":"/paper/thinking-before-looking-improving-multimodal","slug":"thinking-before-looking-improving-multimodal","title":"Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination","date":"2024-11-15","arxiv_id":"2411.12591","repositories_listed":1,"syntology":null},{"url":"/paper/towards-low-resource-harmful-meme-detection","slug":"towards-low-resource-harmful-meme-detection","title":"Towards Low-Resource Harmful Meme Detection with LMM Agents","date":"2024-11-08","arxiv_id":"2411.05383","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-low-resource-harmful-meme-detection#ran","syntology_url":"https://syntology.ai/paper/2411.05383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05383"}},"official":{"repos":["jianzhao-huang/lorehm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-the-role-of-llms-in-multimodal","slug":"understanding-the-role-of-llms-in-multimodal","title":"Understanding the Role of LLMs in Multimodal Evaluation Benchmarks","date":"2024-10-16","arxiv_id":"2410.12329","repositories_listed":1,"syntology":null},{"url":"/paper/journeybench-a-challenging-one-stop-vision","slug":"journeybench-a-challenging-one-stop-vision","title":"JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated Images","date":"2024-09-19","arxiv_id":"2409.12953","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/journeybench-a-challenging-one-stop-vision#ran","syntology_url":"https://syntology.ai/paper/2409.12953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12953"}},"official":{"repos":["journeybench/journeybench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/math-puma-progressive-upward-multimodal","slug":"math-puma-progressive-upward-multimodal","title":"Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning","date":"2024-08-16","arxiv_id":"2408.08640","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/math-puma-progressive-upward-multimodal#ran","syntology_url":"https://syntology.ai/paper/2408.08640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08640"}},"official":{"repos":["wwzhuang01/math-puma"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dc3do-diffusion-classifier-for-3d-objects","slug":"dc3do-diffusion-classifier-for-3d-objects","title":"DC3DO: Diffusion Classifier for 3D Objects","date":"2024-08-13","arxiv_id":"2408.06693","repositories_listed":1,"syntology":null},{"url":"/paper/figure-it-out-analyzing-based-jailbreak","slug":"figure-it-out-analyzing-based-jailbreak","title":"LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models","date":"2024-07-23","arxiv_id":"2407.16205","repositories_listed":1,"syntology":null},{"url":"/paper/haloquest-a-visual-hallucination-dataset-for","slug":"haloquest-a-visual-hallucination-dataset-for","title":"HaloQuest: A Visual Hallucination Dataset for Advancing Multimodal Reasoning","date":"2024-07-22","arxiv_id":"2407.15680","repositories_listed":1,"syntology":null}],"syntology_records":41,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":52,"papers_where_code_ran_first_page":"/task/multimodal-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":4,"url":"/task/multimodal-reasoning/papers/2","json":"/task/multimodal-reasoning/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/multimodal-reasoning/papers/3","json":"/task/multimodal-reasoning/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/multimodal-reasoning/papers/4","json":"/task/multimodal-reasoning/papers/4.json","rows":2},{"order":"ran","page":1,"of":1,"url":"/task/multimodal-reasoning/papers/ran/1","json":"/task/multimodal-reasoning/papers/ran/1.json","rows":52}],"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":"fa9706045a9569951ad7ef4df8c6a560ffdbc13033bdd8bb910aa6421b21b806","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}