{"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":"/dataset/egoschema","name":"EgoSchema","full_name":null,"description_markdown":"**EgoSchema** is very long-form video question-answering dataset, and benchmark to evaluate long video understanding capabilities of modern vision and language systems. Derived from Ego4D, EgoSchema consists of over 5000 human curated multiple choice question answer pairs, spanning over 250 hours of real video data, covering a very broad range of natural human activity and behavior.","description_withheld":null,"homepage":"https://egoschema.github.io/","introduced_date":"2023-08-17","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"},{"name":"Zero-Shot Video Question Answer","url":"/task/zeroshot-video-question-answer","datasets_with_task":"/datasets/task/zeroshot-video-question-answer"}],"languages":[],"variants":["EgoSchema","EgoSchema (subset)","EgoSchema (fullset)"],"data_loaders":[],"num_papers_in_archive":112,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/zero-shot-video-question-answer-on-egoschema-1","task":"Zero-Shot Video Question Answer","dataset_variant":"EgoSchema (fullset)","rows":29,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"BIMBA-LLaVA-Qwen2-7B","paper":"/paper/bimba-selective-scan-compression-for-long","metrics":{"Accuracy":"71.14"},"code_links":[{"title":"md-mohaiminul/BIMBA","url":"https://github.com/md-mohaiminul/BIMBA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-video-question-answer-on-egoschema","task":"Zero-Shot Video Question Answer","dataset_variant":"EgoSchema (subset)","rows":14,"metrics":["Accuracy","Inference Speed (s)"],"first_row_in_archive_order":{"model":"Tarsier (34B)","paper":"/paper/tarsier-recipes-for-training-and-evaluating-1","metrics":{"Accuracy":"68.6"},"code_links":[{"title":"bytedance/tarsier","url":"https://github.com/bytedance/tarsier"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-vqa-on-egoschema","task":"Visual Question Answering (VQA)","dataset_variant":"EgoSchema","rows":1,"metrics":["Acc"],"first_row_in_archive_order":{"model":"Lyra-Pro","paper":"/paper/lyra-an-efficient-and-speech-centric","metrics":{"Acc":"75.8"},"code_links":[{"title":"dvlab-research/Lyra","url":"https://github.com/dvlab-research/Lyra"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":26,"of":26,"counts":{"papers_with_a_benchmark_row":26,"with_a_code_link":26,"where_syntology_ran_a_sample":21,"not_listed_spam_title":0,"listed":26,"listed_where_code_ran":21,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":17,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":17,"listed_every_run_a_failure_of_syntologys_instrument":4,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/qwen2-5-omni-technical-report","slug":"qwen2-5-omni-technical-report","title":"Qwen2.5-Omni Technical Report","date":"2025-03-26","arxiv_id":"2503.20215","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bimba-selective-scan-compression-for-long","slug":"bimba-selective-scan-compression-for-long","title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering","date":"2025-03-12","arxiv_id":"2503.09590","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":6,"samples_unverified":5,"pointer_only_for_licence":4,"official":{"repos":["dvlab-research/Lyra"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":4,"samples_unverified":2,"pointer_only_for_licence":12,"official":{"repos":["gls0425/linvt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/video-rag-visually-aligned-retrieval","slug":"video-rag-visually-aligned-retrieval","title":"Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension","date":"2024-11-20","arxiv_id":"2411.13093","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["leon1207/video-rag-master"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-rag-visually-aligned-retrieval#ran","syntology_url":"https://syntology.ai/paper/2411.13093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.13093"}}}},{"paper":"/paper/ts-llava-constructing-visual-tokens-through","slug":"ts-llava-constructing-visual-tokens-through","title":"TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models","date":"2024-11-17","arxiv_id":"2411.11066","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":7,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["tingyu215/ts-llava"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ts-llava-constructing-visual-tokens-through#ran","syntology_url":"https://syntology.ai/paper/2411.11066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11066"}}}},{"paper":"/paper/timesuite-improving-mllms-for-long-video","slug":"timesuite-improving-mllms-for-long-video","title":"TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning","date":"2024-10-25","arxiv_id":"2410.19702","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/timesuite-improving-mllms-for-long-video#ran","syntology_url":"https://syntology.ai/paper/2410.19702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19702"}}}},{"paper":"/paper/longvu-spatiotemporal-adaptive-compression","slug":"longvu-spatiotemporal-adaptive-compression","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","date":"2024-10-22","arxiv_id":"2410.17434","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":8,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["Vision-CAIR/LongVU"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/longvu-spatiotemporal-adaptive-compression#ran","syntology_url":"https://syntology.ai/paper/2410.17434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17434"}}}},{"paper":"/paper/slowfast-llava-a-strong-training-free","slug":"slowfast-llava-a-strong-training-free","title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","date":"2024-07-22","arxiv_id":"2407.15841","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":6,"official":{"repos":["apple/ml-slowfast-llava"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/slowfast-llava-a-strong-training-free#ran","syntology_url":"https://syntology.ai/paper/2407.15841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15841"}}}},{"paper":"/paper/tarsier-recipes-for-training-and-evaluating-1","slug":"tarsier-recipes-for-training-and-evaluating-1","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","date":"2024-06-30","arxiv_id":"2407.00634","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["bytedance/tarsier"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tarsier-recipes-for-training-and-evaluating-1#ran","syntology_url":"https://syntology.ai/paper/2407.00634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00634"}}}},{"paper":"/paper/too-many-frames-not-all-useful-efficient","slug":"too-many-frames-not-all-useful-efficient","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","date":"2024-06-13","arxiv_id":"2406.09396","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["jongwoopark7978/LVNet"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/too-many-frames-not-all-useful-efficient#ran","syntology_url":"https://syntology.ai/paper/2406.09396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09396"}}}},{"paper":"/paper/videollama-2-advancing-spatial-temporal","slug":"videollama-2-advancing-spatial-temporal","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","date":"2024-06-11","arxiv_id":"2406.07476","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":5,"samples_unverified":5,"pointer_only_for_licence":8,"official":{"repos":["damo-nlp-sg/videollama2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videollama-2-advancing-spatial-temporal#ran","syntology_url":"https://syntology.ai/paper/2406.07476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07476"}}}},{"paper":"/paper/videotree-adaptive-tree-based-video","slug":"videotree-adaptive-tree-based-video","title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","date":"2024-05-29","arxiv_id":"2405.19209","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["Ziyang412/VideoTree"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videotree-adaptive-tree-based-video#ran","syntology_url":"https://syntology.ai/paper/2405.19209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19209"}}}},{"paper":"/paper/traveler-a-multi-lmm-agent-framework-for","slug":"traveler-a-multi-lmm-agent-framework-for","title":"TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering","date":"2024-04-01","arxiv_id":"2404.01476","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/understanding-long-videos-in-one-multimodal","slug":"understanding-long-videos-in-one-multimodal","title":"Understanding Long Videos with Multimodal Language Models","date":"2024-03-25","arxiv_id":"2403.16998","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["kahnchana/mvu"],"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":["found_in_text","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/understanding-long-videos-in-one-multimodal#ran","syntology_url":"https://syntology.ai/paper/2403.16998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16998"}}}},{"paper":"/paper/internvideo2-scaling-video-foundation-models","slug":"internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","arxiv_id":"2403.15377","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/language-repository-for-long-video","slug":"language-repository-for-long-video","title":"Language Repository for Long Video Understanding","date":"2024-03-21","arxiv_id":"2403.14622","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":6,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["kkahatapitiya/langrepo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-repository-for-long-video#ran","syntology_url":"https://syntology.ai/paper/2403.14622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14622"}}}},{"paper":"/paper/video-recap-recursive-captioning-of-hour-long","slug":"video-recap-recursive-captioning-of-hour-long","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","date":"2024-02-20","arxiv_id":"2402.13250","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["md-mohaiminul/VideoRecap"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-recap-recursive-captioning-of-hour-long#ran","syntology_url":"https://syntology.ai/paper/2402.13250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13250"}}}},{"paper":"/paper/a-simple-llm-framework-for-long-range-video","slug":"a-simple-llm-framework-for-long-range-video","title":"A Simple LLM Framework for Long-Range Video Question-Answering","date":"2023-12-28","arxiv_id":"2312.17235","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ceezh/llovi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-simple-llm-framework-for-long-range-video#ran","syntology_url":"https://syntology.ai/paper/2312.17235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17235"}}}},{"paper":"/paper/timechat-a-time-sensitive-multimodal-large","slug":"timechat-a-time-sensitive-multimodal-large","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","date":"2023-12-04","arxiv_id":"2312.02051","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":5,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["renshuhuai-andy/timechat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/timechat-a-time-sensitive-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2312.02051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02051"}}}},{"paper":"/paper/mvbench-a-comprehensive-multi-modal-video","slug":"mvbench-a-comprehensive-multi-modal-video","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","date":"2023-11-28","arxiv_id":"2311.17005","rows_on_this_dataset":5,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":3,"pointer_only_for_licence":2,"official":{"repos":["opengvlab/ask-anything"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mvbench-a-comprehensive-multi-modal-video#ran","syntology_url":"https://syntology.ai/paper/2311.17005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17005"}}}},{"paper":"/paper/vamos-versatile-action-models-for-video","slug":"vamos-versatile-action-models-for-video","title":"Vamos: Versatile Action Models for Video Understanding","date":"2023-11-22","arxiv_id":"2311.13627","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":5,"official":{"repos":["brown-palm/Vamos"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vamos-versatile-action-models-for-video#ran","syntology_url":"https://syntology.ai/paper/2311.13627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13627"}}}},{"paper":"/paper/self-chained-image-language-model-for-video-1","slug":"self-chained-image-language-model-for-video-1","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","date":"2023-05-11","arxiv_id":"2305.06988","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":7,"official":{"repos":["yui010206/sevila"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-chained-image-language-model-for-video-1#ran","syntology_url":"https://syntology.ai/paper/2305.06988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.06988"}}}},{"paper":"/paper/mplug-owl-modularization-empowers-large","slug":"mplug-owl-modularization-empowers-large","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","date":"2023-04-27","arxiv_id":"2304.14178","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/internvideo-general-video-foundation-models","slug":"internvideo-general-video-foundation-models","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","date":"2022-12-06","arxiv_id":"2212.03191","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["opengvlab/internvideo"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/internvideo-general-video-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.03191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03191"}}}},{"paper":"/paper/zero-shot-video-question-answering-via-frozen","slug":"zero-shot-video-question-answering-via-frozen","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","date":"2022-06-16","arxiv_id":"2206.08155","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":34,"samples_ran":14,"samples_constructed":9,"samples_ran_checked":14,"samples_ran_instrument_failed":0,"samples_unverified":20,"pointer_only_for_licence":1,"official":{"repos":["antoyang/FrozenBiLM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/zero-shot-video-question-answering-via-frozen#ran","syntology_url":"https://syntology.ai/paper/2206.08155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08155"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/qwen2-5-omni-technical-report","slug":"qwen2-5-omni-technical-report","title":"Qwen2.5-Omni Technical Report","date":"2025-03-26","arxiv_id":"2503.20215","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bimba-selective-scan-compression-for-long","slug":"bimba-selective-scan-compression-for-long","title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering","date":"2025-03-12","arxiv_id":"2503.09590","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":6,"samples_unverified":5,"pointer_only_for_licence":4,"official":{"repos":["dvlab-research/Lyra"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":4,"samples_unverified":2,"pointer_only_for_licence":12,"official":{"repos":["gls0425/linvt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/video-rag-visually-aligned-retrieval","slug":"video-rag-visually-aligned-retrieval","title":"Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension","date":"2024-11-20","arxiv_id":"2411.13093","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["leon1207/video-rag-master"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-rag-visually-aligned-retrieval#ran","syntology_url":"https://syntology.ai/paper/2411.13093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.13093"}}}},{"paper":"/paper/ts-llava-constructing-visual-tokens-through","slug":"ts-llava-constructing-visual-tokens-through","title":"TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models","date":"2024-11-17","arxiv_id":"2411.11066","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":7,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["tingyu215/ts-llava"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ts-llava-constructing-visual-tokens-through#ran","syntology_url":"https://syntology.ai/paper/2411.11066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11066"}}}},{"paper":"/paper/timesuite-improving-mllms-for-long-video","slug":"timesuite-improving-mllms-for-long-video","title":"TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning","date":"2024-10-25","arxiv_id":"2410.19702","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/timesuite-improving-mllms-for-long-video#ran","syntology_url":"https://syntology.ai/paper/2410.19702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19702"}}}},{"paper":"/paper/longvu-spatiotemporal-adaptive-compression","slug":"longvu-spatiotemporal-adaptive-compression","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","date":"2024-10-22","arxiv_id":"2410.17434","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":8,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["Vision-CAIR/LongVU"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/longvu-spatiotemporal-adaptive-compression#ran","syntology_url":"https://syntology.ai/paper/2410.17434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17434"}}}},{"paper":"/paper/slowfast-llava-a-strong-training-free","slug":"slowfast-llava-a-strong-training-free","title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","date":"2024-07-22","arxiv_id":"2407.15841","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":6,"official":{"repos":["apple/ml-slowfast-llava"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/slowfast-llava-a-strong-training-free#ran","syntology_url":"https://syntology.ai/paper/2407.15841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15841"}}}},{"paper":"/paper/tarsier-recipes-for-training-and-evaluating-1","slug":"tarsier-recipes-for-training-and-evaluating-1","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","date":"2024-06-30","arxiv_id":"2407.00634","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["bytedance/tarsier"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tarsier-recipes-for-training-and-evaluating-1#ran","syntology_url":"https://syntology.ai/paper/2407.00634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00634"}}}},{"paper":"/paper/too-many-frames-not-all-useful-efficient","slug":"too-many-frames-not-all-useful-efficient","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","date":"2024-06-13","arxiv_id":"2406.09396","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["jongwoopark7978/LVNet"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/too-many-frames-not-all-useful-efficient#ran","syntology_url":"https://syntology.ai/paper/2406.09396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09396"}}}},{"paper":"/paper/videollama-2-advancing-spatial-temporal","slug":"videollama-2-advancing-spatial-temporal","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","date":"2024-06-11","arxiv_id":"2406.07476","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":5,"samples_unverified":5,"pointer_only_for_licence":8,"official":{"repos":["damo-nlp-sg/videollama2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videollama-2-advancing-spatial-temporal#ran","syntology_url":"https://syntology.ai/paper/2406.07476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07476"}}}},{"paper":"/paper/videotree-adaptive-tree-based-video","slug":"videotree-adaptive-tree-based-video","title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","date":"2024-05-29","arxiv_id":"2405.19209","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["Ziyang412/VideoTree"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videotree-adaptive-tree-based-video#ran","syntology_url":"https://syntology.ai/paper/2405.19209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19209"}}}},{"paper":"/paper/traveler-a-multi-lmm-agent-framework-for","slug":"traveler-a-multi-lmm-agent-framework-for","title":"TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering","date":"2024-04-01","arxiv_id":"2404.01476","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/understanding-long-videos-in-one-multimodal","slug":"understanding-long-videos-in-one-multimodal","title":"Understanding Long Videos with Multimodal Language Models","date":"2024-03-25","arxiv_id":"2403.16998","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["kahnchana/mvu"],"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":["found_in_text","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/understanding-long-videos-in-one-multimodal#ran","syntology_url":"https://syntology.ai/paper/2403.16998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16998"}}}},{"paper":"/paper/internvideo2-scaling-video-foundation-models","slug":"internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","arxiv_id":"2403.15377","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/language-repository-for-long-video","slug":"language-repository-for-long-video","title":"Language Repository for Long Video Understanding","date":"2024-03-21","arxiv_id":"2403.14622","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":6,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["kkahatapitiya/langrepo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-repository-for-long-video#ran","syntology_url":"https://syntology.ai/paper/2403.14622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14622"}}}},{"paper":"/paper/video-recap-recursive-captioning-of-hour-long","slug":"video-recap-recursive-captioning-of-hour-long","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","date":"2024-02-20","arxiv_id":"2402.13250","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["md-mohaiminul/VideoRecap"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-recap-recursive-captioning-of-hour-long#ran","syntology_url":"https://syntology.ai/paper/2402.13250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13250"}}}},{"paper":"/paper/a-simple-llm-framework-for-long-range-video","slug":"a-simple-llm-framework-for-long-range-video","title":"A Simple LLM Framework for Long-Range Video Question-Answering","date":"2023-12-28","arxiv_id":"2312.17235","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ceezh/llovi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-simple-llm-framework-for-long-range-video#ran","syntology_url":"https://syntology.ai/paper/2312.17235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17235"}}}},{"paper":"/paper/timechat-a-time-sensitive-multimodal-large","slug":"timechat-a-time-sensitive-multimodal-large","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","date":"2023-12-04","arxiv_id":"2312.02051","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":5,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["renshuhuai-andy/timechat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/timechat-a-time-sensitive-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2312.02051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02051"}}}},{"paper":"/paper/mvbench-a-comprehensive-multi-modal-video","slug":"mvbench-a-comprehensive-multi-modal-video","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","date":"2023-11-28","arxiv_id":"2311.17005","rows_on_this_dataset":5,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":3,"pointer_only_for_licence":2,"official":{"repos":["opengvlab/ask-anything"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mvbench-a-comprehensive-multi-modal-video#ran","syntology_url":"https://syntology.ai/paper/2311.17005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17005"}}}},{"paper":"/paper/vamos-versatile-action-models-for-video","slug":"vamos-versatile-action-models-for-video","title":"Vamos: Versatile Action Models for Video Understanding","date":"2023-11-22","arxiv_id":"2311.13627","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":5,"official":{"repos":["brown-palm/Vamos"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vamos-versatile-action-models-for-video#ran","syntology_url":"https://syntology.ai/paper/2311.13627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13627"}}}},{"paper":"/paper/self-chained-image-language-model-for-video-1","slug":"self-chained-image-language-model-for-video-1","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","date":"2023-05-11","arxiv_id":"2305.06988","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":7,"official":{"repos":["yui010206/sevila"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-chained-image-language-model-for-video-1#ran","syntology_url":"https://syntology.ai/paper/2305.06988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.06988"}}}},{"paper":"/paper/mplug-owl-modularization-empowers-large","slug":"mplug-owl-modularization-empowers-large","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","date":"2023-04-27","arxiv_id":"2304.14178","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/internvideo-general-video-foundation-models","slug":"internvideo-general-video-foundation-models","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","date":"2022-12-06","arxiv_id":"2212.03191","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["opengvlab/internvideo"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/internvideo-general-video-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.03191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03191"}}}},{"paper":"/paper/zero-shot-video-question-answering-via-frozen","slug":"zero-shot-video-question-answering-via-frozen","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","date":"2022-06-16","arxiv_id":"2206.08155","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":34,"samples_ran":14,"samples_constructed":9,"samples_ran_checked":14,"samples_ran_instrument_failed":0,"samples_unverified":20,"pointer_only_for_licence":1,"official":{"repos":["antoyang/FrozenBiLM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/zero-shot-video-question-answering-via-frozen#ran","syntology_url":"https://syntology.ai/paper/2206.08155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08155"}}}}],"papers_where_code_ran":21,"papers_where_code_ran_first_page":"/dataset/egoschema/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/egoschema/papers/ran/1","json":"/dataset/egoschema/papers/ran/1.json","rows":21}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":21,"samples_harvested":194,"samples_ran":155,"samples_constructed":10,"samples_ran_checked":81,"samples_ran_instrument_failed":74,"samples_unverified":39,"pointer_only_for_licence":57,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":21,"papers_with_a_run_with_no_instrument_failure":17,"papers_where_every_run_was_an_instrument_failure":4,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":3,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/zero-shot-video-question-answer-on-egoschema","since_archive":"/sota/zero-shot-video-question-answer-on-egoschema#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/visual-question-answering-vqa-on-egoschema","since_archive":"/sota/visual-question-answering-vqa-on-egoschema#since-judged","papers_judged":3,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"784330949cf05e0746a8808565ccb1fe6bc899f73a32468267036a89b66ecf2f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}