{"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/zeroshot-video-question-answer","name":"Zero-Shot Video Question Answer","slug":"zeroshot-video-question-answer","description_markdown":"This task present the results of Zeroshot Question Answer results on TGIF-QA dataset for LLM powered Video Conversational Models.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":85,"papers_with_code":73,"benchmarks":17,"benchmark_tables_in_archive":17,"benchmark_tables_shown":17,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":18,"subtasks":0,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/zeroshot-video-question-answer-on-msrvtt-qa","slug":"zeroshot-video-question-answer-on-msrvtt-qa","dataset":"MSRVTT-QA","dataset_url":"/dataset/msrvtt-qa","rows_in_archive":30,"metrics":["Accuracy","Confidence Score"],"first_row_in_archive_order":{"model":"Flash-VStream","paper_title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","paper_url":"/paper/flash-vstream-memory-based-real-time","paper_date":"2024-06-12","arxiv_id":"2406.08085","code_links":[{"title":"IVGSZ/Flash-VStream","url":"https://github.com/IVGSZ/Flash-VStream"}],"syntology":null}},{"leaderboard":"/sota/zero-shot-video-question-answer-on-egoschema-1","slug":"zero-shot-video-question-answer-on-egoschema-1","dataset":"EgoSchema (fullset)","dataset_url":"/dataset/egoschema","rows_in_archive":29,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"BIMBA-LLaVA-Qwen2-7B","paper_title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering","paper_url":"/paper/bimba-selective-scan-compression-for-long","paper_date":"2025-03-12","arxiv_id":"2503.09590","code_links":[{"title":"md-mohaiminul/BIMBA","url":"https://github.com/md-mohaiminul/BIMBA"}],"syntology":null}},{"leaderboard":"/sota/zeroshot-video-question-answer-on-activitynet","slug":"zeroshot-video-question-answer-on-activitynet","dataset":"ActivityNet-QA","dataset_url":"/dataset/activitynet-qa","rows_in_archive":28,"metrics":["Accuracy","Confidence Score"],"first_row_in_archive_order":{"model":"Tarsier (34B)","paper_title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","paper_url":"/paper/tarsier-recipes-for-training-and-evaluating-1","paper_date":"2024-06-30","arxiv_id":"2407.00634","code_links":[{"title":"bytedance/tarsier","url":"https://github.com/bytedance/tarsier"}],"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/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"}},"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"]}}}},{"leaderboard":"/sota/zeroshot-video-question-answer-on-msvd-qa","slug":"zeroshot-video-question-answer-on-msvd-qa","dataset":"MSVD-QA","dataset_url":"/dataset/msvd-qa","rows_in_archive":28,"metrics":["Accuracy","Confidence Score"],"first_row_in_archive_order":{"model":"Tarsier (34B)","paper_title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","paper_url":"/paper/tarsier-recipes-for-training-and-evaluating-1","paper_date":"2024-06-30","arxiv_id":"2407.00634","code_links":[{"title":"bytedance/tarsier","url":"https://github.com/bytedance/tarsier"}],"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/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"}},"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"]}}}},{"leaderboard":"/sota/zero-shot-video-question-answer-on-next-qa","slug":"zero-shot-video-question-answer-on-next-qa","dataset":"NExT-QA","dataset_url":"/dataset/next-qa","rows_in_archive":27,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"VideoMultiAgent (GPT-4o)","paper_title":"VideoMultiAgents: A Multi-Agent Framework for Video Question Answering","paper_url":"/paper/videomultiagents-a-multi-agent-framework-for","paper_date":"2025-04-25","arxiv_id":"2504.20091","code_links":[{"title":"panasonicconnect/videomultiagents","url":"https://github.com/panasonicconnect/videomultiagents"}],"syntology":null}},{"leaderboard":"/sota/zero-shot-video-question-answer-on-egoschema","slug":"zero-shot-video-question-answer-on-egoschema","dataset":"EgoSchema (subset)","dataset_url":"/dataset/egoschema","rows_in_archive":14,"metrics":["Accuracy","Inference Speed (s)"],"first_row_in_archive_order":{"model":"Tarsier (34B)","paper_title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","paper_url":"/paper/tarsier-recipes-for-training-and-evaluating-1","paper_date":"2024-06-30","arxiv_id":"2407.00634","code_links":[{"title":"bytedance/tarsier","url":"https://github.com/bytedance/tarsier"}],"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/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"}},"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"]}}}},{"leaderboard":"/sota/zeroshot-video-question-answer-on-tgif-qa","slug":"zeroshot-video-question-answer-on-tgif-qa","dataset":"TGIF-QA","dataset_url":"/dataset/tgif-qa","rows_in_archive":14,"metrics":["Accuracy","Confidence Score"],"first_row_in_archive_order":{"model":"Tarsier (34B)","paper_title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","paper_url":"/paper/tarsier-recipes-for-training-and-evaluating-1","paper_date":"2024-06-30","arxiv_id":"2407.00634","code_links":[{"title":"bytedance/tarsier","url":"https://github.com/bytedance/tarsier"}],"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/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"}},"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"]}}}},{"leaderboard":"/sota/zero-shot-video-question-answer-on-intentqa","slug":"zero-shot-video-question-answer-on-intentqa","dataset":"IntentQA","dataset_url":"/dataset/intentqa","rows_in_archive":13,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ENTER","paper_title":"ENTER: Event Based Interpretable Reasoning for VideoQA","paper_url":"/paper/enter-event-based-interpretable-reasoning-for","paper_date":"2025-01-24","arxiv_id":"2501.14194","code_links":[],"syntology":null}},{"leaderboard":"/sota/zero-shot-video-question-answer-on-video-mme-1","slug":"zero-shot-video-question-answer-on-video-mme-1","dataset":"Video-MME","dataset_url":"/dataset/video-mme","rows_in_archive":11,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Gemini 1.5 Pro","paper_title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","paper_url":"/paper/gemini-1-5-unlocking-multimodal-understanding","paper_date":"2024-03-08","arxiv_id":"2403.05530","code_links":[{"title":"dlvuldet/primevul","url":"https://github.com/dlvuldet/primevul"}],"syntology":null}},{"leaderboard":"/sota/zero-shot-video-question-answer-on-next-gqa","slug":"zero-shot-video-question-answer-on-next-gqa","dataset":"NExT-GQA","dataset_url":"/dataset/next-gqa","rows_in_archive":9,"metrics":["Acc@GQA"],"first_row_in_archive_order":{"model":"DeVi (Gemini 2.0)","paper_title":"Question-Answering Dense Video Events","paper_url":"/paper/question-answering-dense-video-events","paper_date":"2024-09-06","arxiv_id":"2409.04388","code_links":[{"title":"qhuni/deve-qa","url":"https://github.com/qhuni/deve-qa"}],"syntology":null}},{"leaderboard":"/sota/zero-shot-video-question-answer-on-tvqa","slug":"zero-shot-video-question-answer-on-tvqa","dataset":"TVQA","dataset_url":"/dataset/tvqa","rows_in_archive":9,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"FrozenBiLM (with speech)","paper_title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","paper_url":"/paper/zero-shot-video-question-answering-via-frozen","paper_date":"2022-06-16","arxiv_id":"2206.08155","code_links":[{"title":"antoyang/FrozenBiLM","url":"https://github.com/antoyang/FrozenBiLM"},{"title":"klauscc/dam","url":"https://github.com/klauscc/dam"},{"title":"sts-vlcc/sts-vlcc","url":"https://github.com/sts-vlcc/sts-vlcc"}],"syntology":{"n":34,"n_ran":14,"n_constructed":9,"n_ran_checked":14,"n_instrument":0,"n_unverified":20,"n_honours":1,"n_violates":1,"n_no_contract":12,"n_pointer_only":1,"phrase":"14 ran (of which 9 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 20 unverified","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"}},"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"]}}}},{"leaderboard":"/sota/zero-shot-video-question-answer-on-video-mme","slug":"zero-shot-video-question-answer-on-video-mme","dataset":"Video-MME (w/o subs)","dataset_url":"/dataset/video-mme","rows_in_archive":9,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Video-RAG (based on LLaVA-Video)","paper_title":"Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension","paper_url":"/paper/video-rag-visually-aligned-retrieval","paper_date":"2024-11-20","arxiv_id":"2411.13093","code_links":[{"title":"leon1207/video-rag-master","url":"https://github.com/leon1207/video-rag-master"}],"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}}},{"leaderboard":"/sota/zero-shot-video-question-answer-on-vnbench","slug":"zero-shot-video-question-answer-on-vnbench","dataset":"VNBench","dataset_url":"/dataset/vnbench","rows_in_archive":9,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"BIMBA-LLaVA-Qwen2-7B","paper_title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering","paper_url":"/paper/bimba-selective-scan-compression-for-long","paper_date":"2025-03-12","arxiv_id":"2503.09590","code_links":[{"title":"md-mohaiminul/BIMBA","url":"https://github.com/md-mohaiminul/BIMBA"}],"syntology":null}},{"leaderboard":"/sota/zero-shot-video-question-answer-on-star","slug":"zero-shot-video-question-answer-on-star","dataset":"STAR Benchmark","dataset_url":"/dataset/situated-reasoning-star","rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"VideoChat2","paper_title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","paper_url":"/paper/mvbench-a-comprehensive-multi-modal-video","paper_date":"2023-11-28","arxiv_id":"2311.17005","code_links":[{"title":"opengvlab/ask-anything","url":"https://github.com/opengvlab/ask-anything"},{"title":"magic-research/PLLaVA","url":"https://github.com/magic-research/PLLaVA"},{"title":"bytedance/tarsier","url":"https://github.com/bytedance/tarsier"}],"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":2,"phrase":"7 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; 4 where Syntology's instrument failed) · 3 unverified","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"}},"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"]}}}},{"leaderboard":"/sota/zero-shot-video-question-answer-on-zero-shot","slug":"zero-shot-video-question-answer-on-zero-shot","dataset":"Zero-shot Video Question Answering on LongVideoBench","dataset_url":"/dataset/zero-shot-video-question-answering-on","rows_in_archive":4,"metrics":["Accuracy (% )"],"first_row_in_archive_order":{"model":"Gemini 1.5 Pro","paper_title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","paper_url":"/paper/gemini-1-5-unlocking-multimodal-understanding","paper_date":"2024-03-08","arxiv_id":"2403.05530","code_links":[{"title":"dlvuldet/primevul","url":"https://github.com/dlvuldet/primevul"}],"syntology":null}},{"leaderboard":"/sota/zero-shot-video-question-answer-on-mvbench","slug":"zero-shot-video-question-answer-on-mvbench","dataset":"MVBench","dataset_url":"/dataset/mvbench","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TS-LLaVA-34B","paper_title":"TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models","paper_url":"/paper/ts-llava-constructing-visual-tokens-through","paper_date":"2024-11-17","arxiv_id":"2411.11066","code_links":[{"title":"tingyu215/ts-llava","url":"https://github.com/tingyu215/ts-llava"}],"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":3,"n_instrument":7,"n_unverified":1,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"10 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; 7 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}}},{"leaderboard":"/sota/zero-shot-video-question-answer-on-cinepile-a","slug":"zero-shot-video-question-answer-on-cinepile-a","dataset":"CinePile: A Long Video Question Answering Dataset and Benchmark","dataset_url":"/dataset/cinepile","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Human","paper_title":"CinePile: A Long Video Question Answering Dataset and Benchmark","paper_url":"/paper/cinepile-a-long-video-question-answering","paper_date":"2024-05-14","arxiv_id":"2405.08813","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/next-qa","name":"NExT-QA","full_name":"","num_papers_in_archive":174},{"url":"/dataset/video-mme","name":"Video-MME","full_name":"","num_papers_in_archive":152},{"url":"/dataset/activitynet-qa","name":"ActivityNet-QA","full_name":"","num_papers_in_archive":146},{"url":"/dataset/tvqa","name":"TVQA","full_name":"TVQA","num_papers_in_archive":146},{"url":"/dataset/mvbench","name":"MVBench","full_name":"","num_papers_in_archive":139},{"url":"/dataset/egoschema","name":"EgoSchema","full_name":"","num_papers_in_archive":112},{"url":"/dataset/tgif-qa","name":"TGIF-QA","full_name":"TGIF-QA","num_papers_in_archive":92},{"url":"/dataset/msrvtt-qa","name":"MSRVTT-QA","full_name":"","num_papers_in_archive":66},{"url":"/dataset/msvd-qa","name":"MSVD-QA","full_name":"","num_papers_in_archive":61},{"url":"/dataset/tvqa-1","name":"TVQA+","full_name":"","num_papers_in_archive":60},{"url":"/dataset/intentqa","name":"IntentQA","full_name":"","num_papers_in_archive":27},{"url":"/dataset/next-gqa","name":"NExT-GQA","full_name":"","num_papers_in_archive":23},{"url":"/dataset/situated-reasoning-star","name":"STAR Benchmark","full_name":"Situated Reasoning","num_papers_in_archive":17},{"url":"/dataset/neptune","name":"Neptune","full_name":"Neptune Long Video Understanding Benchmark","num_papers_in_archive":12},{"url":"/dataset/vnbench","name":"VNBench","full_name":"","num_papers_in_archive":11},{"url":"/dataset/zero-shot-video-question-answering-on","name":"Zero-shot Video Question Answering on LongVideoBench","full_name":"A Benchmark for Long-context Interleaved Video-Language Understanding","num_papers_in_archive":5},{"url":"/dataset/shot2story20k","name":"Shot2Story20K","full_name":"","num_papers_in_archive":3},{"url":"/dataset/cinepile","name":"CinePile: A Long Video Question Answering Dataset and Benchmark","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/question-answering","name":"Question Answering"},{"url":"/task/video-question-answering","name":"Video Question Answering"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":85,"of":85,"of_with_code":73,"tagged_in_all":85,"counts":{"archive_papers_tagged":85,"with_a_code_link":73,"where_syntology_ran_a_sample":45,"not_listed_spam_title":0,"listed":85,"listed_where_code_ran":45,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":38,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":38,"listed_every_run_a_failure_of_syntologys_instrument":7,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/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":1,"n_no_contract":5,"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, 1 violated, 5 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/video-llava-learning-united-visual-1","slug":"video-llava-learning-united-visual-1","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","date":"2023-11-16","arxiv_id":"2311.10122","repositories_listed":6,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/video-llava-learning-united-visual-1#ran","syntology_url":"https://syntology.ai/paper/2311.10122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.10122"}},"official":{"repos":["PKU-YuanGroup/Video-LLaVA"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/mistral-7b","slug":"mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","repositories_listed":6,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}},"official":{"repos":["mistralai/mistral-src"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/flamingo-a-visual-language-model-for-few-shot-1","slug":"flamingo-a-visual-language-model-for-few-shot-1","title":"Flamingo: a Visual Language Model for Few-Shot Learning","date":"2022-04-29","arxiv_id":"2204.14198","repositories_listed":5,"syntology":{"n":24,"n_ran":18,"n_constructed":6,"n_ran_checked":11,"n_instrument":7,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":8,"phrase":"18 ran (of which 6 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/flamingo-a-visual-language-model-for-few-shot-1#ran","syntology_url":"https://syntology.ai/paper/2204.14198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.14198"}},"official":null}},{"url":"/paper/chat-univi-unified-visual-representation","slug":"chat-univi-unified-visual-representation","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","date":"2023-11-14","arxiv_id":"2311.08046","repositories_listed":4,"syntology":null},{"url":"/paper/video-llama-an-instruction-tuned-audio-visual","slug":"video-llama-an-instruction-tuned-audio-visual","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","date":"2023-06-05","arxiv_id":"2306.02858","repositories_listed":4,"syntology":{"n":25,"n_ran":18,"n_constructed":7,"n_ran_checked":8,"n_instrument":10,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":9,"phrase":"18 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/video-llama-an-instruction-tuned-audio-visual#ran","syntology_url":"https://syntology.ai/paper/2306.02858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02858"}},"official":{"repos":["damo-nlp-sg/video-llama"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/llava-next-interleave-tackling-multi-image","slug":"llava-next-interleave-tackling-multi-image","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","date":"2024-07-10","arxiv_id":"2407.07895","repositories_listed":3,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/llava-next-interleave-tackling-multi-image#ran","syntology_url":"https://syntology.ai/paper/2407.07895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07895"}},"official":{"repos":["LLaVA-VL/LLaVA-NeXT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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","repositories_listed":3,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":5,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":8,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","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"}},"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"]}}},{"url":"/paper/vila-on-pre-training-for-visual-language","slug":"vila-on-pre-training-for-visual-language","title":"VILA: On Pre-training for Visual Language Models","date":"2023-12-12","arxiv_id":"2312.07533","repositories_listed":3,"syntology":null},{"url":"/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","repositories_listed":3,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":2,"phrase":"7 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; 4 where Syntology's instrument failed) · 3 unverified","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"}},"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"]}}},{"url":"/paper/llama-adapter-v2-parameter-efficient-visual","slug":"llama-adapter-v2-parameter-efficient-visual","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","date":"2023-04-28","arxiv_id":"2304.15010","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/llama-adapter-v2-parameter-efficient-visual#ran","syntology_url":"https://syntology.ai/paper/2304.15010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.15010"}},"official":{"repos":["zrrskywalker/llama-adapter"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/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","repositories_listed":3,"syntology":{"n":34,"n_ran":14,"n_constructed":9,"n_ran_checked":14,"n_instrument":0,"n_unverified":20,"n_honours":1,"n_violates":1,"n_no_contract":12,"n_pointer_only":1,"phrase":"14 ran (of which 9 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 20 unverified","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"}},"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"]}}},{"url":"/paper/llava-onevision-easy-visual-task-transfer","slug":"llava-onevision-easy-visual-task-transfer","title":"LLaVA-OneVision: Easy Visual Task Transfer","date":"2024-08-06","arxiv_id":"2408.03326","repositories_listed":2,"syntology":null},{"url":"/paper/2408-01800","slug":"2408-01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","date":"2024-08-03","arxiv_id":"2408.01800","repositories_listed":2,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":2,"n_pointer_only":6,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/2408-01800#ran","syntology_url":"https://syntology.ai/paper/2408.01800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01800"}},"official":{"repos":["OpenBMB/MiniCPM-o"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/long-context-transfer-from-language-to-vision","slug":"long-context-transfer-from-language-to-vision","title":"Long Context Transfer from Language to Vision","date":"2024-06-24","arxiv_id":"2406.16852","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/long-context-transfer-from-language-to-vision#ran","syntology_url":"https://syntology.ai/paper/2406.16852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16852"}},"official":{"repos":["evolvinglmms-lab/longva"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/minigpt4-video-advancing-multimodal-llms-for","slug":"minigpt4-video-advancing-multimodal-llms-for","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","date":"2024-04-04","arxiv_id":"2404.03413","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minigpt4-video-advancing-multimodal-llms-for#ran","syntology_url":"https://syntology.ai/paper/2404.03413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03413"}},"official":{"repos":["Vision-CAIR/MiniGPT4-video"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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","repositories_listed":2,"syntology":null},{"url":"/paper/videoagent-long-form-video-understanding-with","slug":"videoagent-long-form-video-understanding-with","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","date":"2024-03-15","arxiv_id":"2403.10517","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 1 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) · 0 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 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; 5 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/paper/llama-vid-an-image-is-worth-2-tokens-in-large","slug":"llama-vid-an-image-is-worth-2-tokens-in-large","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","date":"2023-11-28","arxiv_id":"2311.17043","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/llama-vid-an-image-is-worth-2-tokens-in-large#ran","syntology_url":"https://syntology.ai/paper/2311.17043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17043"}},"official":{"repos":["dvlab-research/llama-vid"],"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/video-chatgpt-towards-detailed-video","slug":"video-chatgpt-towards-detailed-video","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","date":"2023-06-08","arxiv_id":"2306.05424","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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/internvideo-general-video-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.03191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03191"}},"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"]}}},{"url":"/paper/mvb-a-large-scale-dataset-for-baggage-re","slug":"mvb-a-large-scale-dataset-for-baggage-re","title":"MVB: A Large-Scale Dataset for Baggage Re-Identification and Merged Siamese Networks","date":"2019-07-26","arxiv_id":"1907.11366","repositories_listed":2,"syntology":null},{"url":"/paper/tgif-qa-toward-spatio-temporal-reasoning-in","slug":"tgif-qa-toward-spatio-temporal-reasoning-in","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","date":"2017-04-14","arxiv_id":"1704.04497","repositories_listed":2,"syntology":null},{"url":"/paper/videomultiagents-a-multi-agent-framework-for","slug":"videomultiagents-a-multi-agent-framework-for","title":"VideoMultiAgents: A Multi-Agent Framework for Video Question Answering","date":"2025-04-25","arxiv_id":"2504.20091","repositories_listed":1,"syntology":null},{"url":"/paper/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","repositories_listed":1,"syntology":null},{"url":"/paper/agentic-keyframe-search-for-video-question","slug":"agentic-keyframe-search-for-video-question","title":"Agentic Keyframe Search for Video Question Answering","date":"2025-03-20","arxiv_id":"2503.16032","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":2,"n_honours":1,"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; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/agentic-keyframe-search-for-video-question#ran","syntology_url":"https://syntology.ai/paper/2503.16032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16032"}},"official":{"repos":["fansunqi/akeys"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/videomind-a-chain-of-lora-agent-for-long","slug":"videomind-a-chain-of-lora-agent-for-long","title":"VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning","date":"2025-03-17","arxiv_id":"2503.13444","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videomind-a-chain-of-lora-agent-for-long#ran","syntology_url":"https://syntology.ai/paper/2503.13444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.13444"}},"official":{"repos":["yeliudev/VideoMind"],"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/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","repositories_listed":1,"syntology":null},{"url":"/paper/llava-mini-efficient-image-and-video-large","slug":"llava-mini-efficient-image-and-video-large","title":"LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token","date":"2025-01-07","arxiv_id":"2501.03895","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 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) · 0 unverified","sample_list":"/paper/llava-mini-efficient-image-and-video-large#ran","syntology_url":"https://syntology.ai/paper/2501.03895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.03895"}},"official":{"repos":["ictnlp/llava-mini"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vidctx-context-aware-video-question-answering","slug":"vidctx-context-aware-video-question-answering","title":"VidCtx: Context-aware Video Question Answering with Image Models","date":"2024-12-23","arxiv_id":"2412.17415","repositories_listed":1,"syntology":null},{"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":6,"n_instrument":4,"n_unverified":2,"n_honours":3,"n_violates":1,"n_no_contract":2,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 4 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":3,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":3,"n_instrument":7,"n_unverified":1,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"10 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; 7 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/paper/ppllava-varied-video-sequence-understanding","slug":"ppllava-varied-video-sequence-understanding","title":"PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance","date":"2024-11-04","arxiv_id":"2411.02327","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":2,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ppllava-varied-video-sequence-understanding#ran","syntology_url":"https://syntology.ai/paper/2411.02327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02327"}},"official":{"repos":["farewellthree/ppllava"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/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"}},"official":null}},{"url":"/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","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":3,"n_instrument":8,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"11 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; 8 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/question-answering-dense-video-events","slug":"question-answering-dense-video-events","title":"Question-Answering Dense Video Events","date":"2024-09-06","arxiv_id":"2409.04388","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":6,"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) · 1 unverified","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"}},"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"]}}},{"url":"/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","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/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"}},"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"]}}},{"url":"/paper/needle-in-a-video-haystack-a-scalable","slug":"needle-in-a-video-haystack-a-scalable","title":"Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs","date":"2024-06-13","arxiv_id":"2406.09367","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":3,"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/needle-in-a-video-haystack-a-scalable#ran","syntology_url":"https://syntology.ai/paper/2406.09367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09367"}},"official":{"repos":["joez17/videoniah"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/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","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/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"}},"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"]}}},{"url":"/paper/videogpt-integrating-image-and-video-encoders","slug":"videogpt-integrating-image-and-video-encoders","title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","date":"2024-06-13","arxiv_id":"2406.09418","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/videogpt-integrating-image-and-video-encoders#ran","syntology_url":"https://syntology.ai/paper/2406.09418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09418"}},"official":{"repos":["mbzuai-oryx/videogpt-plus"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/flash-vstream-memory-based-real-time","slug":"flash-vstream-memory-based-real-time","title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","date":"2024-06-12","arxiv_id":"2406.08085","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/pllava-parameter-free-llava-extension-from-1","slug":"pllava-parameter-free-llava-extension-from-1","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","date":"2024-04-25","arxiv_id":"2404.16994","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/pllava-parameter-free-llava-extension-from-1#ran","syntology_url":"https://syntology.ai/paper/2404.16994","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16994"}},"official":{"repos":["magic-research/PLLaVA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/an-image-grid-can-be-worth-a-video-zero-shot","slug":"an-image-grid-can-be-worth-a-video-zero-shot","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","date":"2024-03-27","arxiv_id":"2403.18406","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/an-image-grid-can-be-worth-a-video-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2403.18406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18406"}},"official":{"repos":["imagegridworth/IG-VLM"],"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/elysium-exploring-object-level-perception-in","slug":"elysium-exploring-object-level-perception-in","title":"Elysium: Exploring Object-level Perception in Videos via MLLM","date":"2024-03-25","arxiv_id":"2403.16558","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"7 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/elysium-exploring-object-level-perception-in#ran","syntology_url":"https://syntology.ai/paper/2403.16558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16558"}},"official":{"repos":["hon-wong/elysium"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/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"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/vid-tldr-training-free-token-merging-for","slug":"vid-tldr-training-free-token-merging-for","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","date":"2024-03-20","arxiv_id":"2403.13347","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/vid-tldr-training-free-token-merging-for#ran","syntology_url":"https://syntology.ai/paper/2403.13347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13347"}},"official":{"repos":["mlvlab/vid-tldr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/gemini-1-5-unlocking-multimodal-understanding","slug":"gemini-1-5-unlocking-multimodal-understanding","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","date":"2024-03-08","arxiv_id":"2403.05530","repositories_listed":1,"syntology":null},{"url":"/paper/cat-enhancing-multimodal-large-language-model","slug":"cat-enhancing-multimodal-large-language-model","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","date":"2024-03-07","arxiv_id":"2403.04640","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":5,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/cat-enhancing-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2403.04640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04640"}},"official":{"repos":["rikeilong/bay-cat"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/question-instructed-visual-descriptions-for","slug":"question-instructed-visual-descriptions-for","title":"Question-Instructed Visual Descriptions for Zero-Shot Video Question Answering","date":"2024-02-16","arxiv_id":"2402.10698","repositories_listed":1,"syntology":null},{"url":"/paper/video-lavit-unified-video-language-pre","slug":"video-lavit-unified-video-language-pre","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","date":"2024-02-05","arxiv_id":"2402.03161","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/video-lavit-unified-video-language-pre#ran","syntology_url":"https://syntology.ai/paper/2402.03161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03161"}},"official":null}},{"url":"/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","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/shot2story20k-a-new-benchmark-for","slug":"shot2story20k-a-new-benchmark-for","title":"Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos","date":"2023-12-16","arxiv_id":"2312.10300","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/shot2story20k-a-new-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2312.10300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10300"}},"official":{"repos":["bytedance/Shot2Story"],"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"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":1,"n_no_contract":2,"n_pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/one-for-all-video-conversation-is-feasible","slug":"one-for-all-video-conversation-is-feasible","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","date":"2023-09-27","arxiv_id":"2309.15785","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/one-for-all-video-conversation-is-feasible#ran","syntology_url":"https://syntology.ai/paper/2309.15785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15785"}},"official":{"repos":["farewellthree/BT-Adapter"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-and-few-shot-video-question","slug":"zero-shot-and-few-shot-video-question","title":"Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts","date":"2023-09-27","arxiv_id":"2309.15915","repositories_listed":1,"syntology":null},{"url":"/paper/egoschema-a-diagnostic-benchmark-for-very-1","slug":"egoschema-a-diagnostic-benchmark-for-very-1","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","date":"2023-08-17","arxiv_id":"2308.09126","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/egoschema-a-diagnostic-benchmark-for-very-1#ran","syntology_url":"https://syntology.ai/paper/2308.09126","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09126"}},"official":{"repos":["egoschema/egoschema"],"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/omnidatacomposer-a-unified-data-structure-for","slug":"omnidatacomposer-a-unified-data-structure-for","title":"OmniDataComposer: A Unified Data Structure for Multimodal Data Fusion and Infinite Data Generation","date":"2023-08-08","arxiv_id":"2308.04126","repositories_listed":1,"syntology":null},{"url":"/paper/moviechat-from-dense-token-to-sparse-memory","slug":"moviechat-from-dense-token-to-sparse-memory","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","date":"2023-07-31","arxiv_id":"2307.16449","repositories_listed":1,"syntology":null},{"url":"/paper/valley-video-assistant-with-large-language","slug":"valley-video-assistant-with-large-language","title":"Valley: Video Assistant with Large Language model Enhanced abilitY","date":"2023-06-12","arxiv_id":"2306.07207","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/paper/videochat-chat-centric-video-understanding","slug":"videochat-chat-centric-video-understanding","title":"VideoChat: Chat-Centric Video Understanding","date":"2023-05-10","arxiv_id":"2305.06355","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/verbs-in-action-improving-verb-understanding","slug":"verbs-in-action-improving-verb-understanding","title":"Verbs in Action: Improving verb understanding in video-language models","date":"2023-04-13","arxiv_id":"2304.06708","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/verbs-in-action-improving-verb-understanding#ran","syntology_url":"https://syntology.ai/paper/2304.06708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.06708"}},"official":{"repos":["google-research/scenic"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vipergpt-visual-inference-via-python","slug":"vipergpt-visual-inference-via-python","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","date":"2023-03-14","arxiv_id":"2303.08128","repositories_listed":1,"syntology":null},{"url":"/paper/provably-efficient-neural-offline","slug":"provably-efficient-neural-offline","title":"VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation","date":"2023-02-24","arxiv_id":"2302.12780","repositories_listed":1,"syntology":null},{"url":"/paper/activitynet-qa-a-dataset-for-understanding","slug":"activitynet-qa-a-dataset-for-understanding","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","date":"2019-06-06","arxiv_id":"1906.02467","repositories_listed":1,"syntology":null},{"url":"/paper/enter-event-based-interpretable-reasoning-for","slug":"enter-event-based-interpretable-reasoning-for","title":"ENTER: Event Based Interpretable Reasoning for VideoQA","date":"2025-01-24","arxiv_id":"2501.14194","repositories_listed":0,"syntology":null},{"url":"/paper/gpt-4o-system-card","slug":"gpt-4o-system-card","title":"GPT-4o System Card","date":"2024-10-25","arxiv_id":"2410.21276","repositories_listed":0,"syntology":null},{"url":"/paper/video-instruction-tuning-with-synthetic-data","slug":"video-instruction-tuning-with-synthetic-data","title":"Video Instruction Tuning With Synthetic Data","date":"2024-10-03","arxiv_id":"2410.02713","repositories_listed":0,"syntology":null},{"url":"/paper/gpt-4o-visual-perception-performance-of","slug":"gpt-4o-visual-perception-performance-of","title":"GPT-4o: Visual perception performance of multimodal large language models in piglet activity understanding","date":"2024-06-14","arxiv_id":"2406.09781","repositories_listed":0,"syntology":null},{"url":"/paper/short-film-dataset-sfd-a-benchmark-for-story","slug":"short-film-dataset-sfd-a-benchmark-for-story","title":"Long Story Short: Story-level Video Understanding from 20K Short Films","date":"2024-06-14","arxiv_id":"2406.10221","repositories_listed":0,"syntology":null},{"url":"/paper/deepstack-deeply-stacking-visual-tokens-is","slug":"deepstack-deeply-stacking-visual-tokens-is","title":"DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs","date":"2024-06-06","arxiv_id":"2406.04334","repositories_listed":0,"syntology":null},{"url":"/paper/streaming-long-video-understanding-with-large","slug":"streaming-long-video-understanding-with-large","title":"Streaming Long Video Understanding with Large Language Models","date":"2024-05-25","arxiv_id":"2405.16009","repositories_listed":0,"syntology":null},{"url":"/paper/cinepile-a-long-video-question-answering","slug":"cinepile-a-long-video-question-answering","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","date":"2024-05-14","arxiv_id":"2405.08813","repositories_listed":0,"syntology":null},{"url":"/paper/morevqa-exploring-modular-reasoning-models","slug":"morevqa-exploring-modular-reasoning-models","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","date":"2024-04-09","arxiv_id":"2404.06511","repositories_listed":0,"syntology":null},{"url":"/paper/vista-llama-reliable-video-narrator-via-equal","slug":"vista-llama-reliable-video-narrator-via-equal","title":"Vista-LLaMA: Reliable Video Narrator via Equal Distance to Visual Tokens","date":"2023-12-12","arxiv_id":"2312.08870","repositories_listed":0,"syntology":null},{"url":"/paper/zero-shot-video-question-answering-with","slug":"zero-shot-video-question-answering-with","title":"Zero-Shot Video Question Answering with Procedural Programs","date":"2023-12-01","arxiv_id":"2312.00937","repositories_listed":0,"syntology":null},{"url":"/paper/0-1-deep-neural-networks-via-block-coordinate","slug":"0-1-deep-neural-networks-via-block-coordinate","title":"0/1 Deep Neural Networks via Block Coordinate Descent","date":"2022-06-19","arxiv_id":"2206.09379","repositories_listed":0,"syntology":null}],"syntology_records":47,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":10,"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/zeroshot-video-question-answer-on-msrvtt-qa","since_archive":"/sota/zeroshot-video-question-answer-on-msrvtt-qa#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/zeroshot-video-question-answer-on-activitynet","since_archive":"/sota/zeroshot-video-question-answer-on-activitynet#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/zeroshot-video-question-answer-on-msvd-qa","since_archive":"/sota/zeroshot-video-question-answer-on-msvd-qa#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/zero-shot-video-question-answer-on-next-qa","since_archive":"/sota/zero-shot-video-question-answer-on-next-qa#since-judged","papers_judged":2,"placed":0},{"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/zeroshot-video-question-answer-on-tgif-qa","since_archive":"/sota/zeroshot-video-question-answer-on-tgif-qa#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/zero-shot-video-question-answer-on-intentqa","since_archive":"/sota/zero-shot-video-question-answer-on-intentqa#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/zero-shot-video-question-answer-on-video-mme-1","since_archive":"/sota/zero-shot-video-question-answer-on-video-mme-1#since-judged","papers_judged":3,"placed":0},{"leaderboard":"/sota/zero-shot-video-question-answer-on-vnbench","since_archive":"/sota/zero-shot-video-question-answer-on-vnbench#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/zero-shot-video-question-answer-on-mvbench","since_archive":"/sota/zero-shot-video-question-answer-on-mvbench#since-judged","papers_judged":2,"placed":0}]},"papers_where_code_ran":45,"papers_where_code_ran_first_page":"/task/zeroshot-video-question-answer/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/zeroshot-video-question-answer/papers/ran/1","json":"/task/zeroshot-video-question-answer/papers/ran/1.json","rows":45}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"c21ed2d84b84d908c451ef232c93221af1472ecc3d5b4e9441a9a6ea37fea06d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}