{"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-question-answering-1/papers/ran/1","list_of":"/task/visual-question-answering-1","task":"Visual Question Answering","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","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.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":4,"rows_per_page":100,"rows":[1,100],"of":378,"counts":{"archive_papers_tagged":2177,"with_a_code_link":1042,"where_syntology_ran_a_sample":378,"not_listed_spam_title":0,"listed":2177,"listed_where_code_ran":378,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":308,"every_run_a_failure_of_syntologys_instrument":70,"listed_with_a_run_with_no_instrument_failure":308,"listed_every_run_a_failure_of_syntologys_instrument":70,"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"},"first_page":"/task/visual-question-answering-1/papers/ran/1","prev":null,"next":"/task/visual-question-answering-1/papers/ran/2","papers":[{"url":"/paper/simpledoc-multi-modal-document-understanding","slug":"simpledoc-multi-modal-document-understanding","title":"SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement","date":"2025-06-16","arxiv_id":"2506.14035","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/simpledoc-multi-modal-document-understanding#ran","syntology_url":"https://syntology.ai/paper/2506.14035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.14035"}},"official":{"repos":["ag2ai/simpledoc"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/slotpi-physics-informed-object-centric","slug":"slotpi-physics-informed-object-centric","title":"SlotPi: Physics-informed Object-centric Reasoning Models","date":"2025-06-12","arxiv_id":"2506.10778","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/slotpi-physics-informed-object-centric#ran","syntology_url":"https://syntology.ai/paper/2506.10778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.10778"}},"official":{"repos":["intell-sci-comput/slotpi"],"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":["official"]}}},{"url":"/paper/an-open-source-software-toolkit-benchmark","slug":"an-open-source-software-toolkit-benchmark","title":"An Open-Source Software Toolkit & Benchmark Suite for the Evaluation and Adaptation of Multimodal Action Models","date":"2025-06-10","arxiv_id":"2506.09172","repositories_listed":0,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/an-open-source-software-toolkit-benchmark#ran","syntology_url":"https://syntology.ai/paper/2506.09172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.09172"}},"official":null}},{"url":"/paper/mineanybuild-benchmarking-spatial-planning","slug":"mineanybuild-benchmarking-spatial-planning","title":"MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents","date":"2025-05-26","arxiv_id":"2505.20148","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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/mineanybuild-benchmarking-spatial-planning#ran","syntology_url":"https://syntology.ai/paper/2505.20148","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20148"}},"official":{"repos":["mineanybuild/mineanybuild"],"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/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/infochartqa-a-benchmark-for-multimodal","slug":"infochartqa-a-benchmark-for-multimodal","title":"InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts","date":"2025-05-25","arxiv_id":"2505.19028","repositories_listed":3,"syntology":{"n":20,"n_ran":19,"n_constructed":0,"n_ran_checked":16,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":3,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/infochartqa-a-benchmark-for-multimodal#ran","syntology_url":"https://syntology.ai/paper/2505.19028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19028"}},"official":{"repos":["cooldawnant/infochartqa"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"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/cxreasonbench-a-benchmark-for-evaluating","slug":"cxreasonbench-a-benchmark-for-evaluating","title":"CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays","date":"2025-05-23","arxiv_id":"2505.18087","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/cxreasonbench-a-benchmark-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2505.18087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18087"}},"official":{"repos":["ttumyche/cxreasonbench"],"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/benchmarking-retrieval-augmented-multimomal","slug":"benchmarking-retrieval-augmented-multimomal","title":"Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering","date":"2025-05-22","arxiv_id":"2505.16470","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/benchmarking-retrieval-augmented-multimomal#ran","syntology_url":"https://syntology.ai/paper/2505.16470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16470"}},"official":{"repos":["mmdocrag/mmdocrag"],"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/medagentboard-benchmarking-multi-agent","slug":"medagentboard-benchmarking-multi-agent","title":"MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks","date":"2025-05-18","arxiv_id":"2505.12371","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"11 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; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/medagentboard-benchmarking-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2505.12371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12371"}},"official":{"repos":["yhzhu99/medagentboard"],"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":["found_in_text"]}}},{"url":"/paper/omgm-orchestrate-multiple-granularities-and","slug":"omgm-orchestrate-multiple-granularities-and","title":"OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval","date":"2025-05-10","arxiv_id":"2505.07879","repositories_listed":0,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/omgm-orchestrate-multiple-granularities-and#ran","syntology_url":"https://syntology.ai/paper/2505.07879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.07879"}},"official":null}},{"url":"/paper/adcare-vlm-leveraging-large-vision-language","slug":"adcare-vlm-leveraging-large-vision-language","title":"AdCare-VLM: Leveraging Large Vision Language Model (LVLM) to Monitor Long-Term Medication Adherence and Care","date":"2025-05-01","arxiv_id":"2505.00275","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/adcare-vlm-leveraging-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2505.00275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.00275"}},"official":{"repos":["asad14053/AdCare-VLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/unlearning-sensitive-information-in","slug":"unlearning-sensitive-information-in","title":"Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation","date":"2025-05-01","arxiv_id":"2505.01456","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unlearning-sensitive-information-in#ran","syntology_url":"https://syntology.ai/paper/2505.01456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.01456"}},"official":{"repos":["vaidehi99/unlok-vqa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/illume-illuminating-unified-mllm-with-dual","slug":"illume-illuminating-unified-mllm-with-dual","title":"ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement","date":"2025-04-02","arxiv_id":"2504.01934","repositories_listed":1,"syntology":{"n":20,"n_ran":19,"n_constructed":0,"n_ran_checked":18,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":17,"n_pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 1 violated, 17 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/illume-illuminating-unified-mllm-with-dual#ran","syntology_url":"https://syntology.ai/paper/2504.01934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.01934"}},"official":null}},{"url":"/paper/opendrivevla-towards-end-to-end-autonomous","slug":"opendrivevla-towards-end-to-end-autonomous","title":"OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model","date":"2025-03-30","arxiv_id":"2503.23463","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"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) · 5 unverified","sample_list":"/paper/opendrivevla-towards-end-to-end-autonomous#ran","syntology_url":"https://syntology.ai/paper/2503.23463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.23463"}},"official":{"repos":["DriveVLA/OpenDriveVLA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/facebench-a-multi-view-multi-level-facial","slug":"facebench-a-multi-view-multi-level-facial","title":"FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMs","date":"2025-03-27","arxiv_id":"2503.21457","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/facebench-a-multi-view-multi-level-facial#ran","syntology_url":"https://syntology.ai/paper/2503.21457","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21457"}},"official":{"repos":["cvi-szu/facebench"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mind-the-gap-benchmarking-spatial-reasoning","slug":"mind-the-gap-benchmarking-spatial-reasoning","title":"Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models","date":"2025-03-25","arxiv_id":"2503.19707","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mind-the-gap-benchmarking-spatial-reasoning#ran","syntology_url":"https://syntology.ai/paper/2503.19707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.19707"}},"official":{"repos":["stogiannidis/srbench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/med3dvlm-an-efficient-vision-language-model","slug":"med3dvlm-an-efficient-vision-language-model","title":"Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis","date":"2025-03-25","arxiv_id":"2503.20047","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/med3dvlm-an-efficient-vision-language-model#ran","syntology_url":"https://syntology.ai/paper/2503.20047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.20047"}},"official":{"repos":["mirthai/med3dvlm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/marten-visual-question-answering-with-mask","slug":"marten-visual-question-answering-with-mask","title":"Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding","date":"2025-03-18","arxiv_id":"2503.14140","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/marten-visual-question-answering-with-mask#ran","syntology_url":"https://syntology.ai/paper/2503.14140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14140"}},"official":null}},{"url":"/paper/simlingo-vision-only-closed-loop-autonomous","slug":"simlingo-vision-only-closed-loop-autonomous","title":"SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment","date":"2025-03-12","arxiv_id":"2503.09594","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":8,"n_ran_checked":8,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/simlingo-vision-only-closed-loop-autonomous#ran","syntology_url":"https://syntology.ai/paper/2503.09594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09594"}},"official":null}},{"url":"/paper/re-align-aligning-vision-language-models-via","slug":"re-align-aligning-vision-language-models-via","title":"Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization","date":"2025-02-18","arxiv_id":"2502.13146","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/re-align-aligning-vision-language-models-via#ran","syntology_url":"https://syntology.ai/paper/2502.13146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13146"}},"official":{"repos":["taco-group/re-align"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/docmia-document-level-membership-inference","slug":"docmia-document-level-membership-inference","title":"DocMIA: Document-Level Membership Inference Attacks against DocVQA Models","date":"2025-02-06","arxiv_id":"2502.03692","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"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) · 2 unverified","sample_list":"/paper/docmia-document-level-membership-inference#ran","syntology_url":"https://syntology.ai/paper/2502.03692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.03692"}},"official":{"repos":["khanhnguyen21006/mia_docvqa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/analyzing-and-boosting-the-power-of-fine","slug":"analyzing-and-boosting-the-power-of-fine","title":"Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models","date":"2025-01-25","arxiv_id":"2501.15140","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/analyzing-and-boosting-the-power-of-fine#ran","syntology_url":"https://syntology.ai/paper/2501.15140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.15140"}},"official":{"repos":["pku-icst-mipl/finedefics_iclr2025"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/generalizing-from-simple-to-hard-visual","slug":"generalizing-from-simple-to-hard-visual","title":"Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?","date":"2025-01-05","arxiv_id":"2501.02669","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":0,"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/generalizing-from-simple-to-hard-visual#ran","syntology_url":"https://syntology.ai/paper/2501.02669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.02669"}},"official":{"repos":["princeton-pli/vlm_s2h"],"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/dual-diffusion-for-unified-image-generation","slug":"dual-diffusion-for-unified-image-generation","title":"Dual Diffusion for Unified Image Generation and Understanding","date":"2024-12-31","arxiv_id":"2501.00289","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dual-diffusion-for-unified-image-generation#ran","syntology_url":"https://syntology.ai/paper/2501.00289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.00289"}},"official":null}},{"url":"/paper/mapeval-a-map-based-evaluation-of-geo-spatial","slug":"mapeval-a-map-based-evaluation-of-geo-spatial","title":"MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models","date":"2024-12-31","arxiv_id":"2501.00316","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":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/mapeval-a-map-based-evaluation-of-geo-spatial#ran","syntology_url":"https://syntology.ai/paper/2501.00316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.00316"}},"official":{"repos":["MapEval/MapEval-API","MapEval/MapEval-Textual","MapEval/MapEval-Visual"],"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/autotrust-benchmarking-trustworthiness-in","slug":"autotrust-benchmarking-trustworthiness-in","title":"AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving","date":"2024-12-19","arxiv_id":"2412.15206","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/autotrust-benchmarking-trustworthiness-in#ran","syntology_url":"https://syntology.ai/paper/2412.15206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15206"}},"official":{"repos":["taco-group/autotrust"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/medcot-medical-chain-of-thought-via","slug":"medcot-medical-chain-of-thought-via","title":"MedCoT: Medical Chain of Thought via Hierarchical Expert","date":"2024-12-18","arxiv_id":"2412.13736","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":2,"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/medcot-medical-chain-of-thought-via#ran","syntology_url":"https://syntology.ai/paper/2412.13736","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.13736"}},"official":{"repos":["jxliu-ai/medcot"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-instruction-tuning-with-500x-fewer","slug":"visual-instruction-tuning-with-500x-fewer","title":"LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering","date":"2024-12-16","arxiv_id":"2412.12359","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/visual-instruction-tuning-with-500x-fewer#ran","syntology_url":"https://syntology.ai/paper/2412.12359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.12359"}},"official":{"repos":["bibisbar/LLaVA-Steering"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/deepseek-vl2-mixture-of-experts-vision","slug":"deepseek-vl2-mixture-of-experts-vision","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","date":"2024-12-13","arxiv_id":"2412.10302","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"phrase":"11 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deepseek-vl2-mixture-of-experts-vision#ran","syntology_url":"https://syntology.ai/paper/2412.10302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10302"}},"official":{"repos":["deepseek-ai/deepseek-vl2"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-a-multimodal-large-language-model","slug":"towards-a-multimodal-large-language-model","title":"Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine","date":"2024-12-12","arxiv_id":"2412.09278","repositories_listed":1,"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":2,"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/towards-a-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2412.09278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09278"}},"official":{"repos":["shawnhuang497/medplib"],"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"]}}},{"url":"/paper/lyra-an-efficient-and-speech-centric","slug":"lyra-an-efficient-and-speech-centric","title":"Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition","date":"2024-12-12","arxiv_id":"2412.09501","repositories_listed":1,"syntology":{"n":19,"n_ran":14,"n_constructed":0,"n_ran_checked":11,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":4,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/lyra-an-efficient-and-speech-centric#ran","syntology_url":"https://syntology.ai/paper/2412.09501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09501"}},"official":{"repos":["dvlab-research/Lyra"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/doe-1-closed-loop-autonomous-driving-with","slug":"doe-1-closed-loop-autonomous-driving-with","title":"Doe-1: Closed-Loop Autonomous Driving with Large World Model","date":"2024-12-12","arxiv_id":"2412.09627","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"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/doe-1-closed-loop-autonomous-driving-with#ran","syntology_url":"https://syntology.ai/paper/2412.09627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09627"}},"official":{"repos":["wzzheng/doe"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/provision-programmatically-scaling-vision","slug":"provision-programmatically-scaling-vision","title":"ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models","date":"2024-12-09","arxiv_id":"2412.07012","repositories_listed":1,"syntology":{"n":15,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":8,"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) · 8 unverified","sample_list":"/paper/provision-programmatically-scaling-vision#ran","syntology_url":"https://syntology.ai/paper/2412.07012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07012"}},"official":{"repos":["jieyuz2/provision"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/linvt-empower-your-image-level-large-language","slug":"linvt-empower-your-image-level-large-language","title":"LinVT: Empower Your Image-level Large Language Model to Understand Videos","date":"2024-12-06","arxiv_id":"2412.05185","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":6,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/linvt-empower-your-image-level-large-language#ran","syntology_url":"https://syntology.ai/paper/2412.05185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05185"}},"official":{"repos":["gls0425/linvt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/expanding-performance-boundaries-of-open","slug":"expanding-performance-boundaries-of-open","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","date":"2024-12-06","arxiv_id":"2412.05271","repositories_listed":1,"syntology":{"n":9,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":8,"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) · 8 unverified","sample_list":"/paper/expanding-performance-boundaries-of-open#ran","syntology_url":"https://syntology.ai/paper/2412.05271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05271"}},"official":{"repos":["opengvlab/internvl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/flashsloth-lightning-multimodal-large","slug":"flashsloth-lightning-multimodal-large","title":"FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression","date":"2024-12-05","arxiv_id":"2412.04317","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/flashsloth-lightning-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2412.04317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.04317"}},"official":{"repos":["codefanw/flashsloth"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/visionzip-longer-is-better-but-not-necessary","slug":"visionzip-longer-is-better-but-not-necessary","title":"VisionZip: Longer is Better but Not Necessary in Vision Language Models","date":"2024-12-05","arxiv_id":"2412.04467","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/visionzip-longer-is-better-but-not-necessary#ran","syntology_url":"https://syntology.ai/paper/2412.04467","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.04467"}},"official":{"repos":["dvlab-research/visionzip"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-stitch-in-time-saves-nine-small-vlm-is-a","slug":"a-stitch-in-time-saves-nine-small-vlm-is-a","title":"A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs","date":"2024-12-04","arxiv_id":"2412.03324","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-stitch-in-time-saves-nine-small-vlm-is-a#ran","syntology_url":"https://syntology.ai/paper/2412.03324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03324"}},"official":{"repos":["NUS-HPC-AI-Lab/SGL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/inst-it-boosting-multimodal-instance","slug":"inst-it-boosting-multimodal-instance","title":"Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning","date":"2024-12-04","arxiv_id":"2412.03565","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/inst-it-boosting-multimodal-instance#ran","syntology_url":"https://syntology.ai/paper/2412.03565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03565"}},"official":{"repos":["inst-it/inst-it"],"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/dynamic-llava-efficient-multimodal-large","slug":"dynamic-llava-efficient-multimodal-large","title":"Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification","date":"2024-12-01","arxiv_id":"2412.00876","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":4,"n_ran_checked":5,"n_instrument":8,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":0,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/dynamic-llava-efficient-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2412.00876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.00876"}},"official":{"repos":["osilly/dynamic_llava"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-modal-information-flow-in-multimodal","slug":"cross-modal-information-flow-in-multimodal","title":"Cross-modal Information Flow in Multimodal Large Language Models","date":"2024-11-27","arxiv_id":"2411.18620","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cross-modal-information-flow-in-multimodal#ran","syntology_url":"https://syntology.ai/paper/2411.18620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.18620"}},"official":{"repos":["FightingFighting/cross-modal-information-flow-in-MLLM"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/zoomeye-enhancing-multimodal-llms-with-human","slug":"zoomeye-enhancing-multimodal-llms-with-human","title":"ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration","date":"2024-11-25","arxiv_id":"2411.16044","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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/zoomeye-enhancing-multimodal-llms-with-human#ran","syntology_url":"https://syntology.ai/paper/2411.16044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.16044"}},"official":{"repos":["om-ai-lab/ZoomEye"],"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/augmenting-multimodal-llms-with-self","slug":"augmenting-multimodal-llms-with-self","title":"Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering","date":"2024-11-25","arxiv_id":"2411.16863","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"8 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/augmenting-multimodal-llms-with-self#ran","syntology_url":"https://syntology.ai/paper/2411.16863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.16863"}},"official":{"repos":["aimagelab/reflectiva"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gmai-vl-gmai-vl-5-5m-a-large-vision-language","slug":"gmai-vl-gmai-vl-5-5m-a-large-vision-language","title":"GMAI-VL & GMAI-VL-5.5M: A Large Vision-Language Model and A Comprehensive Multimodal Dataset Towards General Medical AI","date":"2024-11-21","arxiv_id":"2411.14522","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gmai-vl-gmai-vl-5-5m-a-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2411.14522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14522"}},"official":{"repos":["uni-medical/gmai-vl"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/teaching-vlms-to-localize-specific-objects","slug":"teaching-vlms-to-localize-specific-objects","title":"Teaching VLMs to Localize Specific Objects from In-context Examples","date":"2024-11-20","arxiv_id":"2411.13317","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":4,"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/teaching-vlms-to-localize-specific-objects#ran","syntology_url":"https://syntology.ai/paper/2411.13317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.13317"}},"official":{"repos":["sivandoveh/iploc"],"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/mc-llava-multi-concept-personalized-vision","slug":"mc-llava-multi-concept-personalized-vision","title":"MC-LLaVA: Multi-Concept Personalized Vision-Language Model","date":"2024-11-18","arxiv_id":"2411.11706","repositories_listed":1,"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":1,"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/mc-llava-multi-concept-personalized-vision#ran","syntology_url":"https://syntology.ai/paper/2411.11706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11706"}},"official":{"repos":["arctanxarc/mc-llava"],"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","unlocated"]}}},{"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":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"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, 0 violated, 6 with no contract checked; 0 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":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-multimodal-retrieval-augmented","slug":"benchmarking-multimodal-retrieval-augmented","title":"Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent","date":"2024-11-05","arxiv_id":"2411.02937","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"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) · 2 unverified","sample_list":"/paper/benchmarking-multimodal-retrieval-augmented#ran","syntology_url":"https://syntology.ai/paper/2411.02937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02937"}},"official":{"repos":["alibaba-nlp/omnisearch"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/right-this-way-can-vlms-guide-us-to-see-more","slug":"right-this-way-can-vlms-guide-us-to-see-more","title":"Right this way: Can VLMs Guide Us to See More to Answer Questions?","date":"2024-11-01","arxiv_id":"2411.00394","repositories_listed":1,"syntology":{"n":17,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":13,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/right-this-way-can-vlms-guide-us-to-see-more#ran","syntology_url":"https://syntology.ai/paper/2411.00394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00394"}},"official":{"repos":["LeoLee7/Directional_guidance"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":13,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/show-me-what-and-where-has-changed-question","slug":"show-me-what-and-where-has-changed-question","title":"Show Me What and Where has Changed? Question Answering and Grounding for Remote Sensing Change Detection","date":"2024-10-31","arxiv_id":"2410.23828","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/show-me-what-and-where-has-changed-question#ran","syntology_url":"https://syntology.ai/paper/2410.23828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23828"}},"official":{"repos":["like413/vista"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/autobench-v-can-large-vision-language-models","slug":"autobench-v-can-large-vision-language-models","title":"AutoBench-V: Can Large Vision-Language Models Benchmark Themselves?","date":"2024-10-28","arxiv_id":"2410.21259","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":4,"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/autobench-v-can-large-vision-language-models#ran","syntology_url":"https://syntology.ai/paper/2410.21259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21259"}},"official":{"repos":["wad3birch/AutoBench-V"],"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/progressive-compositionality-in-text-to-image","slug":"progressive-compositionality-in-text-to-image","title":"Progressive Compositionality In Text-to-Image Generative Models","date":"2024-10-22","arxiv_id":"2410.16719","repositories_listed":1,"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/progressive-compositionality-in-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2410.16719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.16719"}},"official":{"repos":["evansh666/evogen"],"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"]}}},{"url":"/paper/multichartqa-benchmarking-vision-language","slug":"multichartqa-benchmarking-vision-language","title":"MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems","date":"2024-10-18","arxiv_id":"2410.14179","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/multichartqa-benchmarking-vision-language#ran","syntology_url":"https://syntology.ai/paper/2410.14179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14179"}},"official":{"repos":["zivenzhu/multi-chart-qa"],"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/worldcuisines-a-massive-scale-benchmark-for","slug":"worldcuisines-a-massive-scale-benchmark-for","title":"WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines","date":"2024-10-16","arxiv_id":"2410.12705","repositories_listed":1,"syntology":{"n":17,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/worldcuisines-a-massive-scale-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2410.12705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12705"}},"official":{"repos":["worldcuisines/worldcuisines"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-foundation-models-for-3d-vision-how","slug":"towards-foundation-models-for-3d-vision-how","title":"Towards Foundation Models for 3D Vision: How Close Are We?","date":"2024-10-14","arxiv_id":"2410.10799","repositories_listed":2,"syntology":{"n":29,"n_ran":20,"n_constructed":0,"n_ran_checked":19,"n_instrument":1,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":1,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/towards-foundation-models-for-3d-vision-how#ran","syntology_url":"https://syntology.ai/paper/2410.10799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10799"}},"official":{"repos":["princeton-vl/uniqa-3d"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/vlfeedback-a-large-scale-ai-feedback-dataset","slug":"vlfeedback-a-large-scale-ai-feedback-dataset","title":"VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment","date":"2024-10-12","arxiv_id":"2410.09421","repositories_listed":0,"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/vlfeedback-a-large-scale-ai-feedback-dataset#ran","syntology_url":"https://syntology.ai/paper/2410.09421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09421"}},"official":null}},{"url":"/paper/voxelprompt-a-vision-language-agent-for","slug":"voxelprompt-a-vision-language-agent-for","title":"VoxelPrompt: A Vision-Language Agent for Grounded Medical Image Analysis","date":"2024-10-10","arxiv_id":"2410.08397","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/voxelprompt-a-vision-language-agent-for#ran","syntology_url":"https://syntology.ai/paper/2410.08397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08397"}},"official":{"repos":["dalcalab/voxel"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/deciphering-cross-modal-alignment-in-large","slug":"deciphering-cross-modal-alignment-in-large","title":"Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate","date":"2024-10-09","arxiv_id":"2410.07167","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deciphering-cross-modal-alignment-in-large#ran","syntology_url":"https://syntology.ai/paper/2410.07167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07167"}},"official":{"repos":["shikiw/modality-integration-rate"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/teochat-a-large-vision-language-assistant-for","slug":"teochat-a-large-vision-language-assistant-for","title":"TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data","date":"2024-10-08","arxiv_id":"2410.06234","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/teochat-a-large-vision-language-assistant-for#ran","syntology_url":"https://syntology.ai/paper/2410.06234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06234"}},"official":{"repos":["ermongroup/teochat"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/llaca-multimodal-large-language-continual","slug":"llaca-multimodal-large-language-continual","title":"Large Continual Instruction Assistant","date":"2024-10-08","arxiv_id":"2410.10868","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/llaca-multimodal-large-language-continual#ran","syntology_url":"https://syntology.ai/paper/2410.10868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10868"}},"official":{"repos":["jingyangqiao/coin"],"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/mc-cot-a-modular-collaborative-cot-framework","slug":"mc-cot-a-modular-collaborative-cot-framework","title":"MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM Integration","date":"2024-10-06","arxiv_id":"2410.04521","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":15,"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/mc-cot-a-modular-collaborative-cot-framework#ran","syntology_url":"https://syntology.ai/paper/2410.04521","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04521"}},"official":{"repos":["thomaswei-cn/MC-CoT"],"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/a-hitchhikers-guide-to-fine-grained-face","slug":"a-hitchhikers-guide-to-fine-grained-face","title":"A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning","date":"2024-10-01","arxiv_id":"2410.00485","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":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) · 2 unverified","sample_list":"/paper/a-hitchhikers-guide-to-fine-grained-face#ran","syntology_url":"https://syntology.ai/paper/2410.00485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00485"}},"official":{"repos":["NickyFot/HitchhikersGuide"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/world-to-code-multi-modal-data-generation-via","slug":"world-to-code-multi-modal-data-generation-via","title":"World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering","date":"2024-09-30","arxiv_id":"2409.20424","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/world-to-code-multi-modal-data-generation-via#ran","syntology_url":"https://syntology.ai/paper/2409.20424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.20424"}},"official":{"repos":["foundation-multimodal-models/world2code"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/t2vs-meet-vlms-a-scalable-multimodal-dataset","slug":"t2vs-meet-vlms-a-scalable-multimodal-dataset","title":"T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition","date":"2024-09-29","arxiv_id":"2409.19734","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"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) · 4 unverified","sample_list":"/paper/t2vs-meet-vlms-a-scalable-multimodal-dataset#ran","syntology_url":"https://syntology.ai/paper/2409.19734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19734"}},"official":{"repos":["nctu-eva-lab/vhd11k"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/emu3-next-token-prediction-is-all-you-need","slug":"emu3-next-token-prediction-is-all-you-need","title":"Emu3: Next-Token Prediction is All You Need","date":"2024-09-27","arxiv_id":"2409.18869","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/emu3-next-token-prediction-is-all-you-need#ran","syntology_url":"https://syntology.ai/paper/2409.18869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18869"}},"official":null}},{"url":"/paper/phantom-of-latent-for-large-language-and","slug":"phantom-of-latent-for-large-language-and","title":"Phantom of Latent for Large Language and Vision Models","date":"2024-09-23","arxiv_id":"2409.14713","repositories_listed":1,"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/phantom-of-latent-for-large-language-and#ran","syntology_url":"https://syntology.ai/paper/2409.14713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.14713"}},"official":{"repos":["byungkwanlee/phantom"],"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/mediconfusion-can-you-trust-your-ai","slug":"mediconfusion-can-you-trust-your-ai","title":"MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models","date":"2024-09-23","arxiv_id":"2409.15477","repositories_listed":2,"syntology":{"n":28,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":16,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":28,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 16 unverified","sample_list":"/paper/mediconfusion-can-you-trust-your-ai#ran","syntology_url":"https://syntology.ai/paper/2409.15477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.15477"}},"official":{"repos":["mshahabsepehri/mediconfusion","AIF4S/MediConfusion"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":16,"ran_from_kinds":["official"]}}},{"url":"/paper/qwen2-vl-enhancing-vision-language-model-s","slug":"qwen2-vl-enhancing-vision-language-model-s","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","date":"2024-09-18","arxiv_id":"2409.12191","repositories_listed":8,"syntology":{"n":12,"n_ran":12,"n_constructed":1,"n_ran_checked":10,"n_instrument":2,"n_unverified":0,"n_honours":4,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/qwen2-vl-enhancing-vision-language-model-s#ran","syntology_url":"https://syntology.ai/paper/2409.12191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12191"}},"official":{"repos":["qwenlm/qwen2-vl"],"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":["listed","official"]}}},{"url":"/paper/less-is-more-a-simple-yet-effective-token","slug":"less-is-more-a-simple-yet-effective-token","title":"Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs","date":"2024-09-17","arxiv_id":"2409.10994","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/less-is-more-a-simple-yet-effective-token#ran","syntology_url":"https://syntology.ai/paper/2409.10994","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.10994"}},"official":{"repos":["freedomintelligence/trim"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lime-m-less-is-more-for-evaluation-of-mllms","slug":"lime-m-less-is-more-for-evaluation-of-mllms","title":"LIME: Less Is More for MLLM Evaluation","date":"2024-09-10","arxiv_id":"2409.06851","repositories_listed":2,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":14,"phrase":"13 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; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lime-m-less-is-more-for-evaluation-of-mllms#ran","syntology_url":"https://syntology.ai/paper/2409.06851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.06851"}},"official":{"repos":["kangreen0210/lime","kangreen0210/lime-m"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/alt-moe-multimodal-alignment-via-alternating","slug":"alt-moe-multimodal-alignment-via-alternating","title":"M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA framework","date":"2024-09-09","arxiv_id":"2409.05929","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/alt-moe-multimodal-alignment-via-alternating#ran","syntology_url":"https://syntology.ai/paper/2409.05929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05929"}},"official":{"repos":["HongyangLL/M3-JEPA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/columbus-evaluating-cognitive-lateral","slug":"columbus-evaluating-cognitive-lateral","title":"COLUMBUS: Evaluating COgnitive Lateral Understanding through Multiple-choice reBUSes","date":"2024-09-06","arxiv_id":"2409.04053","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/columbus-evaluating-cognitive-lateral#ran","syntology_url":"https://syntology.ai/paper/2409.04053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.04053"}},"official":{"repos":["koen-47/columbus"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/how-to-determine-the-preferred-image","slug":"how-to-determine-the-preferred-image","title":"How to Determine the Preferred Image Distribution of a Black-Box Vision-Language Model?","date":"2024-09-03","arxiv_id":"2409.02253","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/how-to-determine-the-preferred-image#ran","syntology_url":"https://syntology.ai/paper/2409.02253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02253"}},"official":{"repos":["asgsaeid/cad_vqa"],"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/cogvlm2-visual-language-models-for-image-and","slug":"cogvlm2-visual-language-models-for-image-and","title":"CogVLM2: Visual Language Models for Image and Video Understanding","date":"2024-08-29","arxiv_id":"2408.16500","repositories_listed":3,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/cogvlm2-visual-language-models-for-image-and#ran","syntology_url":"https://syntology.ai/paper/2408.16500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.16500"}},"official":{"repos":["thudm/cogvlm2","thudm/glm-4"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/fedmeki-a-benchmark-for-scaling-medical","slug":"fedmeki-a-benchmark-for-scaling-medical","title":"FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection","date":"2024-08-17","arxiv_id":"2408.09227","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fedmeki-a-benchmark-for-scaling-medical#ran","syntology_url":"https://syntology.ai/paper/2408.09227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.09227"}},"official":{"repos":["psudslab/FEDMEKI"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/med-pmc-medical-personalized-multi-modal","slug":"med-pmc-medical-personalized-multi-modal","title":"Med-PMC: Medical Personalized Multi-modal Consultation with a Proactive Ask-First-Observe-Next Paradigm","date":"2024-08-16","arxiv_id":"2408.08693","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"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) · 0 unverified","sample_list":"/paper/med-pmc-medical-personalized-multi-modal#ran","syntology_url":"https://syntology.ai/paper/2408.08693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08693"}},"official":{"repos":["liuhc0428/med-pmc"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-agents-as-fast-and-slow-thinkers","slug":"visual-agents-as-fast-and-slow-thinkers","title":"Visual Agents as Fast and Slow Thinkers","date":"2024-08-16","arxiv_id":"2408.08862","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":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-agents-as-fast-and-slow-thinkers#ran","syntology_url":"https://syntology.ai/paper/2408.08862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08862"}},"official":{"repos":["guangyans/sys2-llava"],"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/surgical-vqla-adversarial-contrastive","slug":"surgical-vqla-adversarial-contrastive","title":"Surgical-VQLA++: Adversarial Contrastive Learning for Calibrated Robust Visual Question-Localized Answering in Robotic Surgery","date":"2024-08-09","arxiv_id":"2408.04958","repositories_listed":1,"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":1,"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/surgical-vqla-adversarial-contrastive#ran","syntology_url":"https://syntology.ai/paper/2408.04958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04958"}},"official":{"repos":["longbai1006/surgical-vqlaplus"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-02657","slug":"2408-02657","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining","date":"2024-08-05","arxiv_id":"2408.02657","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2408-02657#ran","syntology_url":"https://syntology.ai/paper/2408.02657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.02657"}},"official":{"repos":["alpha-vllm/lumina-mgpt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/2408-00765","slug":"2408-00765","title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities","date":"2024-08-01","arxiv_id":"2408.00765","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/2408-00765#ran","syntology_url":"https://syntology.ai/paper/2408.00765","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00765"}},"official":{"repos":["yuweihao/mm-vet"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/boosting-audio-visual-question-answering-via","slug":"boosting-audio-visual-question-answering-via","title":"Boosting Audio Visual Question Answering via Key Semantic-Aware Cues","date":"2024-07-30","arxiv_id":"2407.20693","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/boosting-audio-visual-question-answering-via#ran","syntology_url":"https://syntology.ai/paper/2407.20693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.20693"}},"official":{"repos":["gewu-lab/tspm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-a-generalizable-pathology-foundation","slug":"towards-a-generalizable-pathology-foundation","title":"Towards A Generalizable Pathology Foundation Model via Unified Knowledge Distillation","date":"2024-07-26","arxiv_id":"2407.18449","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/towards-a-generalizable-pathology-foundation#ran","syntology_url":"https://syntology.ai/paper/2407.18449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.18449"}},"official":null}},{"url":"/paper/learning-trimodal-relation-for-avqa-with","slug":"learning-trimodal-relation-for-avqa-with","title":"Learning Trimodal Relation for AVQA with Missing Modality","date":"2024-07-23","arxiv_id":"2407.16171","repositories_listed":1,"syntology":{"n":24,"n_ran":20,"n_constructed":14,"n_ran_checked":18,"n_instrument":2,"n_unverified":4,"n_honours":4,"n_violates":0,"n_no_contract":14,"n_pointer_only":3,"phrase":"20 ran (of which 14 constructed an object rather than computing a result; 18 with no instrument failure: 4 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-trimodal-relation-for-avqa-with#ran","syntology_url":"https://syntology.ai/paper/2407.16171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16171"}},"official":{"repos":["visualaikhu/missing-avqa"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":14,"n_ran_no_instrument_failure":15,"n_unverified":4,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/inf-llava-dual-perspective-perception-for","slug":"inf-llava-dual-perspective-perception-for","title":"INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model","date":"2024-07-23","arxiv_id":"2407.16198","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/inf-llava-dual-perspective-perception-for#ran","syntology_url":"https://syntology.ai/paper/2407.16198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16198"}},"official":{"repos":["weihuanglin/inf-llava"],"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","unlocated"]}}},{"url":"/paper/mminstruct-a-high-quality-multi-modal","slug":"mminstruct-a-high-quality-multi-modal","title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","date":"2024-07-22","arxiv_id":"2407.15838","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mminstruct-a-high-quality-multi-modal#ran","syntology_url":"https://syntology.ai/paper/2407.15838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15838"}},"official":{"repos":["yuecao0119/mminstruct"],"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/visual-haystacks-answering-harder-questions","slug":"visual-haystacks-answering-harder-questions","title":"Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark","date":"2024-07-18","arxiv_id":"2407.13766","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/visual-haystacks-answering-harder-questions#ran","syntology_url":"https://syntology.ai/paper/2407.13766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13766"}},"official":{"repos":["visual-haystacks/vhs_benchmark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/densefusion-1m-merging-vision-experts-for","slug":"densefusion-1m-merging-vision-experts-for","title":"DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception","date":"2024-07-11","arxiv_id":"2407.08303","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/densefusion-1m-merging-vision-experts-for#ran","syntology_url":"https://syntology.ai/paper/2407.08303","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08303"}},"official":{"repos":["baaivision/densefusion"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/wsi-vqa-interpreting-whole-slide-images-by","slug":"wsi-vqa-interpreting-whole-slide-images-by","title":"WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question Answering","date":"2024-07-08","arxiv_id":"2407.05603","repositories_listed":1,"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":2,"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/wsi-vqa-interpreting-whole-slide-images-by#ran","syntology_url":"https://syntology.ai/paper/2407.05603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05603"}},"official":{"repos":["cpystan/wsi-vqa"],"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"]}}},{"url":"/paper/minigpt-med-large-language-model-as-a-general","slug":"minigpt-med-large-language-model-as-a-general","title":"MiniGPT-Med: Large Language Model as a General Interface for Radiology Diagnosis","date":"2024-07-04","arxiv_id":"2407.04106","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":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minigpt-med-large-language-model-as-a-general#ran","syntology_url":"https://syntology.ai/paper/2407.04106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04106"}},"official":{"repos":["vision-cair/minigpt-med"],"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/internlm-xcomposer-2-5-a-versatile-large","slug":"internlm-xcomposer-2-5-a-versatile-large","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","date":"2024-07-03","arxiv_id":"2407.03320","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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/internlm-xcomposer-2-5-a-versatile-large#ran","syntology_url":"https://syntology.ai/paper/2407.03320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03320"}},"official":{"repos":["internlm/internlm-xcomposer"],"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/a-bounding-box-is-worth-one-token","slug":"a-bounding-box-is-worth-one-token","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","date":"2024-07-02","arxiv_id":"2407.01976","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":4,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-bounding-box-is-worth-one-token#ran","syntology_url":"https://syntology.ai/paper/2407.01976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01976"}},"official":{"repos":["laytextllm/laytextllm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tokenpacker-efficient-visual-projector-for","slug":"tokenpacker-efficient-visual-projector-for","title":"TokenPacker: Efficient Visual Projector for Multimodal LLM","date":"2024-07-02","arxiv_id":"2407.02392","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/tokenpacker-efficient-visual-projector-for#ran","syntology_url":"https://syntology.ai/paper/2407.02392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02392"}},"official":{"repos":["circleradon/tokenpacker"],"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/stllava-med-self-training-large-language-and","slug":"stllava-med-self-training-large-language-and","title":"STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering","date":"2024-06-28","arxiv_id":"2406.19973","repositories_listed":1,"syntology":{"n":19,"n_ran":9,"n_constructed":4,"n_ran_checked":5,"n_instrument":4,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"9 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/stllava-med-self-training-large-language-and#ran","syntology_url":"https://syntology.ai/paper/2406.19973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19973"}},"official":{"repos":["heliossun/stllava-med"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/llavolta-efficient-multi-modal-models-via","slug":"llavolta-efficient-multi-modal-models-via","title":"Efficient Large Multi-modal Models via Visual Context Compression","date":"2024-06-28","arxiv_id":"2406.20092","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"8 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llavolta-efficient-multi-modal-models-via#ran","syntology_url":"https://syntology.ai/paper/2406.20092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.20092"}},"official":{"repos":["beckschen/llavolta"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mg-llava-towards-multi-granularity-visual","slug":"mg-llava-towards-multi-granularity-visual","title":"MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning","date":"2024-06-25","arxiv_id":"2406.17770","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":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/mg-llava-towards-multi-granularity-visual#ran","syntology_url":"https://syntology.ai/paper/2406.17770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17770"}},"official":{"repos":["phoenixz810/mg-llava"],"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/learnable-in-context-vector-for-visual","slug":"learnable-in-context-vector-for-visual","title":"LIVE: Learnable In-Context Vector for Visual Question Answering","date":"2024-06-19","arxiv_id":"2406.13185","repositories_listed":2,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"3 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; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/learnable-in-context-vector-for-visual#ran","syntology_url":"https://syntology.ai/paper/2406.13185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13185"}},"official":{"repos":["forjadeforest/live-learnable-in-context-vector"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/trol-traversal-of-layers-for-large-language","slug":"trol-traversal-of-layers-for-large-language","title":"TroL: Traversal of Layers for Large Language and Vision Models","date":"2024-06-18","arxiv_id":"2406.12246","repositories_listed":1,"syntology":{"n":30,"n_ran":23,"n_constructed":11,"n_ran_checked":15,"n_instrument":8,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":30,"phrase":"23 ran (of which 11 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/trol-traversal-of-layers-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.12246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12246"}},"official":{"repos":["byungkwanlee/trol"],"state":"official (archive's flag): 23 ran","n_ran":23,"n_constructed":11,"n_ran_no_instrument_failure":15,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/vrsbench-a-versatile-vision-language","slug":"vrsbench-a-versatile-vision-language","title":"VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding","date":"2024-06-18","arxiv_id":"2406.12384","repositories_listed":3,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":13,"phrase":"11 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; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/vrsbench-a-versatile-vision-language#ran","syntology_url":"https://syntology.ai/paper/2406.12384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12384"}},"official":{"repos":["lx709/vrsbench"],"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":["listed","official"]}}},{"url":"/paper/mmdu-a-multi-turn-multi-image-dialog","slug":"mmdu-a-multi-turn-multi-image-dialog","title":"MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs","date":"2024-06-17","arxiv_id":"2406.11833","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":6,"n_honours":2,"n_violates":1,"n_no_contract":1,"n_pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/mmdu-a-multi-turn-multi-image-dialog#ran","syntology_url":"https://syntology.ai/paper/2406.11833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11833"}},"official":{"repos":["liuziyu77/mmdu"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official","unlocated"]}}}],"record_sha256":"04824e285e76caa1547ae3ba5f557718b63509d0a35213ff1cd6c707abbeacb9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}