{"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/video-question-answering","name":"Video Question Answering","slug":"video-question-answering","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":460,"papers_with_code":250,"benchmarks":28,"benchmark_tables_in_archive":28,"benchmark_tables_shown":28,"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":43,"subtasks":2,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/video-question-answering-on-next-qa","slug":"video-question-answering-on-next-qa","dataset":"NExT-QA","dataset_url":"/dataset/next-qa","rows_in_archive":47,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LinVT-Qwen2-VL\n(7B)","paper_title":"LinVT: Empower Your Image-level Large Language Model to Understand Videos","paper_url":"/paper/linvt-empower-your-image-level-large-language","paper_date":"2024-12-06","arxiv_id":"2412.05185","code_links":[{"title":"gls0425/linvt","url":"https://github.com/gls0425/linvt"}],"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"]}}}},{"leaderboard":"/sota/video-question-answering-on-activitynet-qa","slug":"video-question-answering-on-activitynet-qa","dataset":"ActivityNet-QA","dataset_url":"/dataset/activitynet-qa","rows_in_archive":36,"metrics":["Accuracy","Confidence score"],"first_row_in_archive_order":{"model":"GPT-2 + CLIP-14 + CLIP-multilingual (Zero-Shot)","paper_title":"Composing Ensembles of Pre-trained Models via Iterative Consensus","paper_url":"/paper/composing-ensembles-of-pre-trained-models-via","paper_date":"2022-10-20","arxiv_id":"2210.11522","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-question-answering-on-tvbench","slug":"video-question-answering-on-tvbench","dataset":"TVBench","dataset_url":"/dataset/tvbench","rows_in_archive":28,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"Seed1.5-VL thinking","paper_title":"Seed1.5-VL Technical Report","paper_url":"/paper/seed1-5-vl-technical-report","paper_date":"2025-05-11","arxiv_id":"2505.07062","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-question-answering-on-mvbench","slug":"video-question-answering-on-mvbench","dataset":"MVBench","dataset_url":"/dataset/mvbench","rows_in_archive":22,"metrics":["Avg."],"first_row_in_archive_order":{"model":"LinVT-Qwen2-VL\n(7B)","paper_title":"LinVT: Empower Your Image-level Large Language Model to Understand Videos","paper_url":"/paper/linvt-empower-your-image-level-large-language","paper_date":"2024-12-06","arxiv_id":"2412.05185","code_links":[{"title":"gls0425/linvt","url":"https://github.com/gls0425/linvt"}],"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"]}}}},{"leaderboard":"/sota/video-question-answering-on-situated","slug":"video-question-answering-on-situated","dataset":"STAR Benchmark","dataset_url":"/dataset/situated-reasoning-star","rows_in_archive":17,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"VLAP (4 frames)","paper_title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","paper_url":"/paper/vlap-efficient-video-language-alignment-via","paper_date":"2023-12-13","arxiv_id":"2312.08367","code_links":[{"title":"xijun-cs/vila","url":"https://github.com/xijun-cs/vila"}],"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/vlap-efficient-video-language-alignment-via#ran","syntology_url":"https://syntology.ai/paper/2312.08367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08367"}},"official":{"repos":["xijun-cs/vila"],"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/video-question-answering-on-ovbench","slug":"video-question-answering-on-ovbench","dataset":"OVBench","dataset_url":"/dataset/ovbench","rows_in_archive":16,"metrics":["AVG"],"first_row_in_archive_order":{"model":"Seed1.5-VL","paper_title":"Seed1.5-VL Technical Report","paper_url":"/paper/seed1-5-vl-technical-report","paper_date":"2025-05-11","arxiv_id":"2505.07062","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-question-answering-on-msrvtt-qa","slug":"video-question-answering-on-msrvtt-qa","dataset":"MSRVTT-QA","dataset_url":"/dataset/msrvtt-qa","rows_in_archive":14,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Mirasol3B","paper_title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","paper_url":"/paper/mirasol3b-a-multimodal-autoregressive-model","paper_date":"2023-11-09","arxiv_id":"2311.05698","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-question-answering-on-agqa-2-0-balanced","slug":"video-question-answering-on-agqa-2-0-balanced","dataset":"AGQA 2.0 balanced","dataset_url":null,"rows_in_archive":8,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"GF (sup) - Faster RCNN","paper_title":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering","paper_url":"/paper/glance-and-focus-memory-prompting-for-multi-1","paper_date":"2024-01-03","arxiv_id":"2401.01529","code_links":[{"title":"byz0e/glance-focus","url":"https://github.com/byz0e/glance-focus"}],"syntology":{"n":18,"n_ran":14,"n_constructed":2,"n_ran_checked":6,"n_instrument":8,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":7,"phrase":"14 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/glance-and-focus-memory-prompting-for-multi-1#ran","syntology_url":"https://syntology.ai/paper/2401.01529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01529"}},"official":{"repos":["byz0e/glance-focus"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":2,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-question-answering-on-how2qa","slug":"video-question-answering-on-how2qa","dataset":"How2QA","dataset_url":"/dataset/how2qa","rows_in_archive":8,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Text + Text (no Multimodal Pretext Training)","paper_title":"Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval","paper_url":"/paper/towards-fast-adaptation-of-pretrained","paper_date":"2022-06-05","arxiv_id":"2206.02082","code_links":[{"title":"xudonglinthu/upgradable-multimodal-intelligence","url":"https://github.com/xudonglinthu/upgradable-multimodal-intelligence"}],"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":0,"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/towards-fast-adaptation-of-pretrained#ran","syntology_url":"https://syntology.ai/paper/2206.02082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02082"}},"official":{"repos":["xudonglinthu/upgradable-multimodal-intelligence"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-question-answering-on-ivqa","slug":"video-question-answering-on-ivqa","dataset":"iVQA","dataset_url":"/dataset/ivqa","rows_in_archive":7,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Text + Text (no Multimodal Pretext Training)","paper_title":"Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval","paper_url":"/paper/towards-fast-adaptation-of-pretrained","paper_date":"2022-06-05","arxiv_id":"2206.02082","code_links":[{"title":"xudonglinthu/upgradable-multimodal-intelligence","url":"https://github.com/xudonglinthu/upgradable-multimodal-intelligence"}],"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":0,"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/towards-fast-adaptation-of-pretrained#ran","syntology_url":"https://syntology.ai/paper/2206.02082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02082"}},"official":{"repos":["xudonglinthu/upgradable-multimodal-intelligence"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-question-answering-on-msrvtt-mc","slug":"video-question-answering-on-msrvtt-mc","dataset":"MSRVTT-MC","dataset_url":"/dataset/msrvtt-mc","rows_in_archive":7,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"VIOLETv2","paper_title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","paper_url":"/paper/an-empirical-study-of-end-to-end-video","paper_date":"2022-09-04","arxiv_id":"2209.01540","code_links":[{"title":"tsujuifu/pytorch_empirical-mvm","url":"https://github.com/tsujuifu/pytorch_empirical-mvm"}],"syntology":null}},{"leaderboard":"/sota/video-question-answering-on-intentqa","slug":"video-question-answering-on-intentqa","dataset":"IntentQA","dataset_url":"/dataset/intentqa","rows_in_archive":6,"metrics":["Accuarcy","CW","CH","TP&TN"],"first_row_in_archive_order":{"model":"VideoChat2_HD_mistral","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/video-question-answering-on-perception-test","slug":"video-question-answering-on-perception-test","dataset":"Perception Test","dataset_url":"/dataset/perception-test","rows_in_archive":6,"metrics":["Accuracy (Top-1)"],"first_row_in_archive_order":{"model":"Oyrx (34B)","paper_title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","paper_url":"/paper/oryx-mllm-on-demand-spatial-temporal","paper_date":"2024-09-19","arxiv_id":"2409.12961","code_links":[{"title":"oryx-mllm/oryx","url":"https://github.com/oryx-mllm/oryx"}],"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/oryx-mllm-on-demand-spatial-temporal#ran","syntology_url":"https://syntology.ai/paper/2409.12961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12961"}},"official":{"repos":["oryx-mllm/oryx"],"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"]}}}},{"leaderboard":"/sota/video-question-answering-on-sutd-trafficqa","slug":"video-question-answering-on-sutd-trafficqa","dataset":"SUTD-TrafficQA","dataset_url":"/dataset/trafficqa","rows_in_archive":6,"metrics":["1/4","1/2"],"first_row_in_archive_order":{"model":"CFMMC-Align","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/video-question-answering-on-tvqa","slug":"video-question-answering-on-tvqa","dataset":"TVQA","dataset_url":"/dataset/tvqa","rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LLaMA-VQA","paper_title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","paper_url":"/paper/large-language-models-are-temporal-and-causal","paper_date":"2023-10-24","arxiv_id":"2310.15747","code_links":[{"title":"mlvlab/Flipped-VQA","url":"https://github.com/mlvlab/Flipped-VQA"}],"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/large-language-models-are-temporal-and-causal#ran","syntology_url":"https://syntology.ai/paper/2310.15747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15747"}},"official":{"repos":["mlvlab/Flipped-VQA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/video-question-answering-on-wildqa","slug":"video-question-answering-on-wildqa","dataset":"WildQA","dataset_url":"/dataset/wildqa","rows_in_archive":5,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"Multi (text + video, IO)","paper_title":"WildQA: In-the-Wild Video Question Answering","paper_url":"/paper/wildqa-in-the-wild-video-question-answering","paper_date":"2022-09-14","arxiv_id":"2209.06650","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-question-answering-on-lsmdc-mc","slug":"video-question-answering-on-lsmdc-mc","dataset":"LSMDC-MC","dataset_url":null,"rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"VIOLETv2","paper_title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","paper_url":"/paper/an-empirical-study-of-end-to-end-video","paper_date":"2022-09-04","arxiv_id":"2209.01540","code_links":[{"title":"tsujuifu/pytorch_empirical-mvm","url":"https://github.com/tsujuifu/pytorch_empirical-mvm"}],"syntology":null}},{"leaderboard":"/sota/video-question-answering-on-next-qa-efficient","slug":"video-question-answering-on-next-qa-efficient","dataset":"NExT-QA (Efficient)","dataset_url":null,"rows_in_archive":2,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"ViLA (3B, 4 frames)","paper_title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","paper_url":"/paper/vlap-efficient-video-language-alignment-via","paper_date":"2023-12-13","arxiv_id":"2312.08367","code_links":[{"title":"xijun-cs/vila","url":"https://github.com/xijun-cs/vila"}],"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/vlap-efficient-video-language-alignment-via#ran","syntology_url":"https://syntology.ai/paper/2312.08367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08367"}},"official":{"repos":["xijun-cs/vila"],"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/video-question-answering-on-roadtextvqa","slug":"video-question-answering-on-roadtextvqa","dataset":"RoadTextVQA","dataset_url":"/dataset/roadtextvqa","rows_in_archive":2,"metrics":["\t ACCURACY"],"first_row_in_archive_order":{"model":"GIT","paper_title":"Reading Between the Lanes: Text VideoQA on the Road","paper_url":"/paper/reading-between-the-lanes-text-videoqa-on-the","paper_date":"2023-07-08","arxiv_id":"2307.03948","code_links":[{"title":"georg3tom/RoadTextVQA","url":"https://github.com/georg3tom/RoadTextVQA"}],"syntology":null}},{"leaderboard":"/sota/video-question-answering-on-dramaqa","slug":"video-question-answering-on-dramaqa","dataset":"DramaQA","dataset_url":"/dataset/dramaqa","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LLaMA-VQA","paper_title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","paper_url":"/paper/large-language-models-are-temporal-and-causal","paper_date":"2023-10-24","arxiv_id":"2310.15747","code_links":[{"title":"mlvlab/Flipped-VQA","url":"https://github.com/mlvlab/Flipped-VQA"}],"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/large-language-models-are-temporal-and-causal#ran","syntology_url":"https://syntology.ai/paper/2310.15747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15747"}},"official":{"repos":["mlvlab/Flipped-VQA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/video-question-answering-on-howto100m-qa","slug":"video-question-answering-on-howto100m-qa","dataset":"Howto100M-QA","dataset_url":"/dataset/howto100m","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TimeSformer","paper_title":"Is Space-Time Attention All You Need for Video Understanding?","paper_url":"/paper/is-space-time-attention-all-you-need-for","paper_date":"2021-02-09","arxiv_id":"2102.05095","code_links":[{"title":"open-mmlab/mmaction2","url":"https://github.com/open-mmlab/mmaction2"},{"title":"towhee-io/towhee","url":"https://github.com/towhee-io/towhee"},{"title":"facebookresearch/TimeSformer","url":"https://github.com/facebookresearch/TimeSformer"},{"title":"PaddlePaddle/PaddleVideo","url":"https://github.com/PaddlePaddle/PaddleVideo/blob/develop/docs/zh-CN/model_zoo/recognition/timesformer.md"},{"title":"The-AI-Summer/self-attention-cv","url":"https://github.com/The-AI-Summer/self-attention-cv"},{"title":"lucidrains/TimeSformer-pytorch","url":"https://github.com/lucidrains/TimeSformer-pytorch"},{"title":"mx-mark/videotransformer-pytorch","url":"https://github.com/mx-mark/videotransformer-pytorch"},{"title":"jerrywn121/TianChi_AIEarth","url":"https://github.com/jerrywn121/TianChi_AIEarth"},{"title":"davide-coccomini/TimeSformer-Video-Classification","url":"https://github.com/davide-coccomini/TimeSformer-Video-Classification"},{"title":"yiyixuxu/TimeSformer-rolled-attention","url":"https://github.com/yiyixuxu/TimeSformer-rolled-attention"},{"title":"m-bain/video-transformers","url":"https://github.com/m-bain/video-transformers"},{"title":"md-mohaiminul/objectstatechange","url":"https://github.com/md-mohaiminul/objectstatechange"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/timesformer"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/timesformer"},{"title":"pwc-1/Paper-10","url":"https://github.com/pwc-1/Paper-10/tree/main/timesformer"},{"title":"halixness/generative_timesformer_pytorch","url":"https://github.com/halixness/generative_timesformer_pytorch"}],"syntology":{"n":43,"n_ran":35,"n_constructed":17,"n_ran_checked":21,"n_instrument":14,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":20,"n_pointer_only":14,"phrase":"35 ran (of which 17 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 14 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/is-space-time-attention-all-you-need-for#ran","syntology_url":"https://syntology.ai/paper/2102.05095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05095"}},"official":{"repos":["facebookresearch/TimeSformer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}}},{"leaderboard":"/sota/video-question-answering-on-lsmdc-fib","slug":"video-question-answering-on-lsmdc-fib","dataset":"LSMDC-FiB","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Clover","paper_title":"Clover: Towards A Unified Video-Language Alignment and Fusion Model","paper_url":"/paper/clover-towards-a-unified-video-language","paper_date":"2022-07-16","arxiv_id":"2207.07885","code_links":[{"title":"leeyn-43/clover","url":"https://github.com/leeyn-43/clover"}],"syntology":null}},{"leaderboard":"/sota/video-question-answering-on-msr-vtt","slug":"video-question-answering-on-msr-vtt","dataset":"MSR-VTT","dataset_url":"/dataset/msr-vtt","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LocVLM-Vid-B","paper_title":"Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs","paper_url":"/paper/learning-to-localize-objects-improves-spatial","paper_date":"2024-04-11","arxiv_id":"2404.07449","code_links":[{"title":"kahnchana/locvlm","url":"https://github.com/kahnchana/locvlm"}],"syntology":null}},{"leaderboard":"/sota/video-question-answering-on-msr-vtt-mc","slug":"video-question-answering-on-msr-vtt-mc","dataset":"MSR-VTT-MC","dataset_url":"/dataset/msrvtt-mc","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ATP (1<-16)","paper_title":"Revisiting the \"Video\" in Video-Language Understanding","paper_url":"/paper/revisiting-the-video-in-video-language","paper_date":"2022-06-03","arxiv_id":"2206.01720","code_links":[{"title":"stanfordvl/atp-video-language","url":"https://github.com/stanfordvl/atp-video-language"}],"syntology":{"n":5,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/revisiting-the-video-in-video-language#ran","syntology_url":"https://syntology.ai/paper/2206.01720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.01720"}},"official":null}}},{"leaderboard":"/sota/video-question-answering-on-msvd-qa","slug":"video-question-answering-on-msvd-qa","dataset":"MSVD-QA","dataset_url":"/dataset/msvd-qa","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LocVLM-Vid-B","paper_title":"Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs","paper_url":"/paper/learning-to-localize-objects-improves-spatial","paper_date":"2024-04-11","arxiv_id":"2404.07449","code_links":[{"title":"kahnchana/locvlm","url":"https://github.com/kahnchana/locvlm"}],"syntology":null}},{"leaderboard":"/sota/video-question-answering-on-tgif-qa","slug":"video-question-answering-on-tgif-qa","dataset":"TGIF-QA","dataset_url":"/dataset/tgif-qa","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LocVLM-Vid-B","paper_title":"Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs","paper_url":"/paper/learning-to-localize-objects-improves-spatial","paper_date":"2024-04-11","arxiv_id":"2404.07449","code_links":[{"title":"kahnchana/locvlm","url":"https://github.com/kahnchana/locvlm"}],"syntology":null}},{"leaderboard":"/sota/video-question-answering-on-videoqa","slug":"video-question-answering-on-videoqa","dataset":"VideoQA","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Just Ask (fine-tune)","paper_title":"Just Ask: Learning to Answer Questions from Millions of Narrated Videos","paper_url":"/paper/just-ask-learning-to-answer-questions-from","paper_date":"2020-12-01","arxiv_id":"2012.00451","code_links":[{"title":"antoyang/just-ask","url":"https://github.com/antoyang/just-ask"}],"syntology":null}},{"leaderboard":"/sota/video-question-answering-on-vlep","slug":"video-question-answering-on-vlep","dataset":"VLEP","dataset_url":"/dataset/vlep","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LLaMA-VQA","paper_title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","paper_url":"/paper/large-language-models-are-temporal-and-causal","paper_date":"2023-10-24","arxiv_id":"2310.15747","code_links":[{"title":"mlvlab/Flipped-VQA","url":"https://github.com/mlvlab/Flipped-VQA"}],"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/large-language-models-are-temporal-and-causal#ran","syntology_url":"https://syntology.ai/paper/2310.15747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15747"}},"official":{"repos":["mlvlab/Flipped-VQA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}}}],"datasets":[{"url":"/dataset/msr-vtt","name":"MSR-VTT","full_name":"","num_papers_in_archive":640},{"url":"/dataset/howto100m","name":"HowTo100M","full_name":"HowTo100M","num_papers_in_archive":286},{"url":"/dataset/next-qa","name":"NExT-QA","full_name":"","num_papers_in_archive":174},{"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/tgif-qa","name":"TGIF-QA","full_name":"TGIF-QA","num_papers_in_archive":92},{"url":"/dataset/movieqa","name":"MovieQA","full_name":"MovieQA","num_papers_in_archive":86},{"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/tgif","name":"TGIF","full_name":"Tumblr GIF","num_papers_in_archive":51},{"url":"/dataset/agqa","name":"AGQA","full_name":"Action Genome Question Answering","num_papers_in_archive":30},{"url":"/dataset/value","name":"VALUE","full_name":"Video-And-Language Understanding Evaluation","num_papers_in_archive":30},{"url":"/dataset/videoinstruct","name":"VideoInstruct","full_name":"Video Instruction Dataset","num_papers_in_archive":30},{"url":"/dataset/how2qa","name":"How2QA","full_name":"How2QA","num_papers_in_archive":28},{"url":"/dataset/intentqa","name":"IntentQA","full_name":"","num_papers_in_archive":27},{"url":"/dataset/ivqa","name":"iVQA","full_name":"Instructional Video Question Answering","num_papers_in_archive":22},{"url":"/dataset/tvbench","name":"TVBench","full_name":"","num_papers_in_archive":22},{"url":"/dataset/trafficqa","name":"SUTD-TrafficQA","full_name":"","num_papers_in_archive":19},{"url":"/dataset/egotaskqa","name":"EgoTaskQA","full_name":"","num_papers_in_archive":17},{"url":"/dataset/situated-reasoning-star","name":"STAR Benchmark","full_name":"Situated Reasoning","num_papers_in_archive":17},{"url":"/dataset/msrvtt-mc","name":"MSRVTT-MC","full_name":"","num_papers_in_archive":14},{"url":"/dataset/ovbench","name":"OVBench","full_name":"","num_papers_in_archive":14},{"url":"/dataset/dramaqa","name":"DramaQA","full_name":"","num_papers_in_archive":12},{"url":"/dataset/neptune","name":"Neptune","full_name":"Neptune Long Video Understanding Benchmark","num_papers_in_archive":12},{"url":"/dataset/vlep","name":"VLEP","full_name":"Video-and-Language Event Prediction","num_papers_in_archive":11},{"url":"/dataset/perception-test","name":"Perception Test","full_name":"","num_papers_in_archive":10},{"url":"/dataset/knowit-vqa","name":"KnowIT VQA","full_name":"","num_papers_in_archive":9},{"url":"/dataset/vlm2-bench","name":"VLM2-Bench","full_name":"VLM²-Bench","num_papers_in_archive":9},{"url":"/dataset/moviefib","name":"MovieFIB","full_name":"Movie Fill-in-the-Blank","num_papers_in_archive":6},{"url":"/dataset/sqa69m","name":"HowToVQA69M","full_name":"HowToVQA69M","num_papers_in_archive":5},{"url":"/dataset/tutorialvqa","name":"TutorialVQA","full_name":"TutorialVQA","num_papers_in_archive":5},{"url":"/dataset/roadtextvqa","name":"RoadTextVQA","full_name":"","num_papers_in_archive":4},{"url":"/dataset/video-localized-narratives","name":"Video Localized Narratives","full_name":"","num_papers_in_archive":3},{"url":"/dataset/cripp-vqa","name":"CRIPP-VQA","full_name":"Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering","num_papers_in_archive":2},{"url":"/dataset/causalchaos","name":"CausalChaos!","full_name":"CausalChaos!QA","num_papers_in_archive":1},{"url":"/dataset/cinepile","name":"CinePile: A Long Video Question Answering Dataset and Benchmark","full_name":"","num_papers_in_archive":1},{"url":"/dataset/sfd","name":"SF20K","full_name":"Short-Films 20K","num_papers_in_archive":1},{"url":"/dataset/social-iq-2-0","name":"Social-IQ 2.0","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vcg-112k","name":"VCG+112K","full_name":"Video Instruction Dataset 112K","num_papers_in_archive":1},{"url":"/dataset/wildqa","name":"WildQA","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vript","name":"Vript","full_name":"🎬 Vript: A Video Is Worth Thousands of Words","num_papers_in_archive":0}],"subtasks":[{"url":"/task/few-shot-video-question-answering","name":"Few-shot Video Question Answering"},{"url":"/task/zeroshot-video-question-answer","name":"Zero-Shot Video Question Answer"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":5,"rows_per_page":100,"shown":100,"of":460,"of_with_code":250,"tagged_in_all":460,"counts":{"archive_papers_tagged":460,"with_a_code_link":250,"where_syntology_ran_a_sample":124,"not_listed_spam_title":0,"listed":460,"listed_where_code_ran":124,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":104,"every_run_a_failure_of_syntologys_instrument":20,"listed_with_a_run_with_no_instrument_failure":104,"listed_every_run_a_failure_of_syntologys_instrument":20,"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/is-space-time-attention-all-you-need-for","slug":"is-space-time-attention-all-you-need-for","title":"Is Space-Time Attention All You Need for Video Understanding?","date":"2021-02-09","arxiv_id":"2102.05095","repositories_listed":16,"syntology":{"n":43,"n_ran":35,"n_constructed":17,"n_ran_checked":21,"n_instrument":14,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":20,"n_pointer_only":14,"phrase":"35 ran (of which 17 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 14 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/is-space-time-attention-all-you-need-for#ran","syntology_url":"https://syntology.ai/paper/2102.05095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05095"}},"official":{"repos":["facebookresearch/TimeSformer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/visual-instruction-tuning-1","slug":"visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","arxiv_id":"2304.08485","repositories_listed":13,"syntology":{"n":51,"n_ran":16,"n_constructed":6,"n_ran_checked":8,"n_instrument":8,"n_unverified":35,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 35 unverified","sample_list":"/paper/visual-instruction-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2304.08485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08485"}},"official":{"repos":["haotian-liu/LLaVA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["community","listed","named_in_paper","official"]}}},{"url":"/paper/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/minigpt-4-enhancing-vision-language","slug":"minigpt-4-enhancing-vision-language","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","date":"2023-04-20","arxiv_id":"2304.10592","repositories_listed":6,"syntology":null},{"url":"/paper/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/i-srt-aligning-large-multimodal-models-for","slug":"i-srt-aligning-large-multimodal-models-for","title":"ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO","date":"2024-06-17","arxiv_id":"2406.11280","repositories_listed":4,"syntology":{"n":30,"n_ran":26,"n_constructed":0,"n_ran_checked":12,"n_instrument":14,"n_unverified":4,"n_honours":4,"n_violates":2,"n_no_contract":6,"n_pointer_only":15,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 4 honoured, 2 violated, 6 with no contract checked; 14 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/i-srt-aligning-large-multimodal-models-for#ran","syntology_url":"https://syntology.ai/paper/2406.11280","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11280"}},"official":{"repos":["snumprlab/SRT","snumprlab/isr-dpo"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"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/instructblip-towards-general-purpose-vision","slug":"instructblip-towards-general-purpose-vision","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","date":"2023-05-11","arxiv_id":"2305.06500","repositories_listed":4,"syntology":null},{"url":"/paper/video-text-as-game-players-hierarchical","slug":"video-text-as-game-players-hierarchical","title":"Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning","date":"2023-03-25","arxiv_id":"2303.14369","repositories_listed":4,"syntology":{"n":16,"n_ran":12,"n_constructed":7,"n_ran_checked":11,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"12 ran (of which 7 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/video-text-as-game-players-hierarchical#ran","syntology_url":"https://syntology.ai/paper/2303.14369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14369"}},"official":{"repos":["jpthu17/HBI"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mplug-2-a-modularized-multi-modal-foundation","slug":"mplug-2-a-modularized-multi-modal-foundation","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","date":"2023-02-01","arxiv_id":"2302.00402","repositories_listed":4,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":8,"n_instrument":9,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mplug-2-a-modularized-multi-modal-foundation#ran","syntology_url":"https://syntology.ai/paper/2302.00402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00402"}},"official":{"repos":["alibaba/AliceMind"],"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/expectation-maximization-contrastive-learning","slug":"expectation-maximization-contrastive-learning","title":"Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations","date":"2022-11-21","arxiv_id":"2211.11427","repositories_listed":4,"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/expectation-maximization-contrastive-learning#ran","syntology_url":"https://syntology.ai/paper/2211.11427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11427"}},"official":{"repos":["jpthu17/emcl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/tvqa-localized-compositional-video-question","slug":"tvqa-localized-compositional-video-question","title":"TVQA: Localized, Compositional Video Question Answering","date":"2018-09-05","arxiv_id":"1809.01696","repositories_listed":4,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tvqa-localized-compositional-video-question#ran","syntology_url":"https://syntology.ai/paper/1809.01696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.01696"}},"official":null}},{"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/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/trafficqa-a-question-answering-benchmark-and","slug":"trafficqa-a-question-answering-benchmark-and","title":"SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","date":"2021-03-29","arxiv_id":"2103.15538","repositories_listed":3,"syntology":{"n":9,"n_ran":6,"n_constructed":1,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/trafficqa-a-question-answering-benchmark-and#ran","syntology_url":"https://syntology.ai/paper/2103.15538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15538"}},"official":{"repos":["SUTDCV/SUTD-TrafficQA"],"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/hero-hierarchical-encoder-for-video-language","slug":"hero-hierarchical-encoder-for-video-language","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","date":"2020-05-01","arxiv_id":"2005.00200","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hero-hierarchical-encoder-for-video-language#ran","syntology_url":"https://syntology.ai/paper/2005.00200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00200"}},"official":{"repos":["linjieli222/HERO"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/tvqa-spatio-temporal-grounding-for-video","slug":"tvqa-spatio-temporal-grounding-for-video","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","date":"2019-04-25","arxiv_id":"1904.11574","repositories_listed":3,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tvqa-spatio-temporal-grounding-for-video#ran","syntology_url":"https://syntology.ai/paper/1904.11574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11574"}},"official":{"repos":["jayleicn/TVQA-PLUS","jayleicn/TVQAplus"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-models-and-data-for-image-question","slug":"exploring-models-and-data-for-image-question","title":"Exploring Models and Data for Image Question Answering","date":"2015-05-08","arxiv_id":"1505.02074","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/exploring-models-and-data-for-image-question#ran","syntology_url":"https://syntology.ai/paper/1505.02074","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1505.02074"}},"official":{"repos":["renmengye/imageqa-public"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/nvila-efficient-frontier-visual-language","slug":"nvila-efficient-frontier-visual-language","title":"NVILA: Efficient Frontier Visual Language Models","date":"2024-12-05","arxiv_id":"2412.04468","repositories_listed":2,"syntology":null},{"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/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/lstp-language-guided-spatial-temporal-prompt","slug":"lstp-language-guided-spatial-temporal-prompt","title":"Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge","date":"2024-02-25","arxiv_id":"2402.16050","repositories_listed":2,"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":2,"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/lstp-language-guided-spatial-temporal-prompt#ran","syntology_url":"https://syntology.ai/paper/2402.16050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16050"}},"official":{"repos":["bigai-nlco/lstp-chat","bigai-nlco/videotgb"],"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/lingoqa-video-question-answering-for","slug":"lingoqa-video-question-answering-for","title":"LingoQA: Visual Question Answering for Autonomous Driving","date":"2023-12-21","arxiv_id":"2312.14115","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"8 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/lingoqa-video-question-answering-for#ran","syntology_url":"https://syntology.ai/paper/2312.14115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14115"}},"official":{"repos":["wayveai/lingoqa"],"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/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/rtq-rethinking-video-language-understanding","slug":"rtq-rethinking-video-language-understanding","title":"RTQ: Rethinking Video-language Understanding Based on Image-text Model","date":"2023-12-01","arxiv_id":"2312.00347","repositories_listed":2,"syntology":null},{"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/fine-grained-audio-visual-joint","slug":"fine-grained-audio-visual-joint","title":"Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models","date":"2023-10-09","arxiv_id":"2310.05863","repositories_listed":2,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/fine-grained-audio-visual-joint#ran","syntology_url":"https://syntology.ai/paper/2310.05863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05863"}},"official":{"repos":["briansidp/audiovisualllm","the-anonymous-bs/favor"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-pretraining-in-multimodality","slug":"generative-pretraining-in-multimodality","title":"Emu: Generative Pretraining in Multimodality","date":"2023-07-11","arxiv_id":"2307.05222","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/generative-pretraining-in-multimodality#ran","syntology_url":"https://syntology.ai/paper/2307.05222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05222"}},"official":{"repos":["baaivision/emu"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/sas-video-qa-self-adaptive-sampling-for","slug":"sas-video-qa-self-adaptive-sampling-for","title":"Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models","date":"2023-07-09","arxiv_id":"2307.04192","repositories_listed":2,"syntology":null},{"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/pali-x-on-scaling-up-a-multilingual-vision","slug":"pali-x-on-scaling-up-a-multilingual-vision","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","date":"2023-05-29","arxiv_id":"2305.18565","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":4,"n_no_contract":1,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 4 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pali-x-on-scaling-up-a-multilingual-vision#ran","syntology_url":"https://syntology.ai/paper/2305.18565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18565"}},"official":null}},{"url":"/paper/vast-a-vision-audio-subtitle-text-omni-1","slug":"vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","arxiv_id":"2305.18500","repositories_listed":2,"syntology":{"n":42,"n_ran":35,"n_constructed":4,"n_ran_checked":25,"n_instrument":10,"n_unverified":7,"n_honours":4,"n_violates":1,"n_no_contract":20,"n_pointer_only":8,"phrase":"35 ran (of which 4 constructed an object rather than computing a result; 25 with no instrument failure: 4 honoured, 1 violated, 20 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}},"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/visual-causal-scene-refinement-for-video","slug":"visual-causal-scene-refinement-for-video","title":"Visual Causal Scene Refinement for Video Question Answering","date":"2023-05-07","arxiv_id":"2305.04224","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/x-2-vlm-all-in-one-pre-trained-model-for","slug":"x-2-vlm-all-in-one-pre-trained-model-for","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","date":"2022-11-22","arxiv_id":"2211.12402","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/x-2-vlm-all-in-one-pre-trained-model-for#ran","syntology_url":"https://syntology.ai/paper/2211.12402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12402"}},"official":{"repos":["zengyan-97/x2-vlm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/revealing-single-frame-bias-for-video-and","slug":"revealing-single-frame-bias-for-video-and","title":"Revealing Single Frame Bias for Video-and-Language Learning","date":"2022-06-07","arxiv_id":"2206.03428","repositories_listed":2,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/revealing-single-frame-bias-for-video-and#ran","syntology_url":"https://syntology.ai/paper/2206.03428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03428"}},"official":{"repos":["jayleicn/singularity"],"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/revitalize-region-feature-for-democratizing","slug":"revitalize-region-feature-for-democratizing","title":"Revitalize Region Feature for Democratizing Video-Language Pre-training of Retrieval","date":"2022-03-15","arxiv_id":"2203.07720","repositories_listed":2,"syntology":null},{"url":"/paper/assistsr-affordance-centric-question-driven","slug":"assistsr-affordance-centric-question-driven","title":"AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant","date":"2021-11-30","arxiv_id":"2111.15050","repositories_listed":2,"syntology":null},{"url":"/paper/next-qa-next-phase-of-question-answering-to","slug":"next-qa-next-phase-of-question-answering-to","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","date":"2021-05-18","arxiv_id":"2105.08276","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/next-qa-next-phase-of-question-answering-to#ran","syntology_url":"https://syntology.ai/paper/2105.08276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08276"}},"official":{"repos":["doc-doc/NExT-QA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tutorialvqa-question-answering-dataset-for","slug":"tutorialvqa-question-answering-dataset-for","title":"TutorialVQA: Question Answering Dataset for Tutorial Videos","date":"2019-12-02","arxiv_id":"1912.01046","repositories_listed":2,"syntology":null},{"url":"/paper/a-better-way-to-attend-attention-with-trees","slug":"a-better-way-to-attend-attention-with-trees","title":"A Better Way to Attend: Attention with Trees for Video Question Answering","date":"2019-09-05","arxiv_id":"1909.02218","repositories_listed":2,"syntology":null},{"url":"/paper/omninet-a-unified-architecture-for-multi","slug":"omninet-a-unified-architecture-for-multi","title":"OmniNet: A unified architecture for multi-modal multi-task learning","date":"2019-07-17","arxiv_id":"1907.07804","repositories_listed":2,"syntology":null},{"url":"/paper/a-joint-sequence-fusion-model-for-video","slug":"a-joint-sequence-fusion-model-for-video","title":"A Joint Sequence Fusion Model for Video Question Answering and Retrieval","date":"2018-08-07","arxiv_id":"1808.02559","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-joint-sequence-fusion-model-for-video#ran","syntology_url":"https://syntology.ai/paper/1808.02559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.02559"}},"official":null}},{"url":"/paper/decoupled-seg-tokens-make-stronger-reasoning","slug":"decoupled-seg-tokens-make-stronger-reasoning","title":"Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and Grounder","date":"2025-06-28","arxiv_id":"2506.22880","repositories_listed":1,"syntology":null},{"url":"/paper/llava-scissor-token-compression-with-semantic","slug":"llava-scissor-token-compression-with-semantic","title":"LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs","date":"2025-06-27","arxiv_id":"2506.21862","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/llava-scissor-token-compression-with-semantic#ran","syntology_url":"https://syntology.ai/paper/2506.21862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.21862"}},"official":{"repos":["HumanMLLM/LLaVA-Scissor"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/video-salmonn-2-captioning-enhanced-audio","slug":"video-salmonn-2-captioning-enhanced-audio","title":"video-SALMONN 2: Captioning-Enhanced Audio-Visual Large Language Models","date":"2025-06-18","arxiv_id":"2506.15220","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":1,"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/video-salmonn-2-captioning-enhanced-audio#ran","syntology_url":"https://syntology.ai/paper/2506.15220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.15220"}},"official":{"repos":["bytedance/video-salmonn-2"],"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/causalvqa-a-physically-grounded-causal","slug":"causalvqa-a-physically-grounded-causal","title":"CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models","date":"2025-06-11","arxiv_id":"2506.09943","repositories_listed":1,"syntology":null},{"url":"/paper/v-jepa-2-self-supervised-video-models-enable","slug":"v-jepa-2-self-supervised-video-models-enable","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","date":"2025-06-11","arxiv_id":"2506.09985","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/v-jepa-2-self-supervised-video-models-enable#ran","syntology_url":"https://syntology.ai/paper/2506.09985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.09985"}},"official":{"repos":["facebookresearch/vjepa2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/looking-beyond-visible-cues-implicit-video","slug":"looking-beyond-visible-cues-implicit-video","title":"Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning","date":"2025-06-09","arxiv_id":"2506.07811","repositories_listed":1,"syntology":null},{"url":"/paper/egovlm-policy-optimization-for-egocentric","slug":"egovlm-policy-optimization-for-egocentric","title":"EgoVLM: Policy Optimization for Egocentric Video Understanding","date":"2025-06-03","arxiv_id":"2506.03097","repositories_listed":1,"syntology":null},{"url":"/paper/vf-eval-evaluating-multimodal-llms-for","slug":"vf-eval-evaluating-multimodal-llms-for","title":"VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos","date":"2025-05-29","arxiv_id":"2505.23693","repositories_listed":1,"syntology":null},{"url":"/paper/viqagent-zero-shot-video-question-answering","slug":"viqagent-zero-shot-video-question-answering","title":"ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation","date":"2025-05-21","arxiv_id":"2505.15928","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11326","slug":"2505-11326","title":"Temporally-Grounded Language Generation: A Benchmark for Real-Time Vision-Language Models","date":"2025-05-16","arxiv_id":"2505.11326","repositories_listed":1,"syntology":null},{"url":"/paper/videomultiagents-a-multi-agent-framework-for","slug":"videomultiagents-a-multi-agent-framework-for","title":"VideoMultiAgents: A Multi-Agent Framework for Video Question Answering","date":"2025-04-25","arxiv_id":"2504.20091","repositories_listed":1,"syntology":null},{"url":"/paper/perceptionlm-open-access-data-and-models-for","slug":"perceptionlm-open-access-data-and-models-for","title":"PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding","date":"2025-04-17","arxiv_id":"2504.13180","repositories_listed":1,"syntology":null},{"url":"/paper/egotom-benchmarking-theory-of-mind-reasoning","slug":"egotom-benchmarking-theory-of-mind-reasoning","title":"EgoToM: Benchmarking Theory of Mind Reasoning from Egocentric Videos","date":"2025-03-28","arxiv_id":"2503.22152","repositories_listed":1,"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/egotom-benchmarking-theory-of-mind-reasoning#ran","syntology_url":"https://syntology.ai/paper/2503.22152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.22152"}},"official":{"repos":["facebookresearch/egotom"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/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/omnia-de-egotempo-benchmarking-temporal","slug":"omnia-de-egotempo-benchmarking-temporal","title":"Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos","date":"2025-03-17","arxiv_id":"2503.13646","repositories_listed":1,"syntology":null},{"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/streaming-video-question-answering-with-in","slug":"streaming-video-question-answering-with-in","title":"Streaming Video Question-Answering with In-context Video KV-Cache Retrieval","date":"2025-03-01","arxiv_id":"2503.00540","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/streaming-video-question-answering-with-in#ran","syntology_url":"https://syntology.ai/paper/2503.00540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.00540"}},"official":{"repos":["becomebright/rekv"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/egotextvqa-towards-egocentric-scene-text","slug":"egotextvqa-towards-egocentric-scene-text","title":"EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering","date":"2025-02-11","arxiv_id":"2502.07411","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/egotextvqa-towards-egocentric-scene-text#ran","syntology_url":"https://syntology.ai/paper/2502.07411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.07411"}},"official":{"repos":["zhousheng97/egotextvqa"],"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/tumtraffic-videoqa-a-benchmark-for-unified","slug":"tumtraffic-videoqa-a-benchmark-for-unified","title":"TUMTraffic-VideoQA: A Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes","date":"2025-02-04","arxiv_id":"2502.02449","repositories_listed":1,"syntology":null},{"url":"/paper/infty-video-a-training-free-approach-to-long","slug":"infty-video-a-training-free-approach-to-long","title":"$\\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation","date":"2025-01-31","arxiv_id":"2501.19098","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/infty-video-a-training-free-approach-to-long#ran","syntology_url":"https://syntology.ai/paper/2501.19098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.19098"}},"official":{"repos":["deep-spin/infinite-video"],"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/videollama-3-frontier-multimodal-foundation","slug":"videollama-3-frontier-multimodal-foundation","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","date":"2025-01-22","arxiv_id":"2501.13106","repositories_listed":1,"syntology":{"n":14,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"8 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; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/videollama-3-frontier-multimodal-foundation#ran","syntology_url":"https://syntology.ai/paper/2501.13106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.13106"}},"official":{"repos":["damo-nlp-sg/videollama3"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/tarsier2-advancing-large-vision-language","slug":"tarsier2-advancing-large-vision-language","title":"Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding","date":"2025-01-14","arxiv_id":"2501.07888","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tarsier2-advancing-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2501.07888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.07888"}},"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","unlocated"]}}},{"url":"/paper/mecd-unlocking-event-level-causal-graph","slug":"mecd-unlocking-event-level-causal-graph","title":"MECD+: Unlocking Event-Level Causal Graph Discovery for Video Reasoning","date":"2025-01-13","arxiv_id":"2501.07227","repositories_listed":1,"syntology":null},{"url":"/paper/ecbench-can-multi-modal-foundation-models","slug":"ecbench-can-multi-modal-foundation-models","title":"ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark","date":"2025-01-09","arxiv_id":"2501.05031","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ecbench-can-multi-modal-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2501.05031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.05031"}},"official":{"repos":["rh-dang/ecbench"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/online-video-understanding-a-comprehensive","slug":"online-video-understanding-a-comprehensive","title":"Online Video Understanding: OVBench and VideoChat-Online","date":"2024-12-31","arxiv_id":"2501.00584","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-banzhaf-interaction-for-general","slug":"hierarchical-banzhaf-interaction-for-general","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","date":"2024-12-30","arxiv_id":"2412.20964","repositories_listed":1,"syntology":null},{"url":"/paper/video-panda-parameter-efficient-alignment-for","slug":"video-panda-parameter-efficient-alignment-for","title":"Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models","date":"2024-12-24","arxiv_id":"2412.18609","repositories_listed":1,"syntology":null},{"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/friendsqa-a-new-large-scale-deep-video","slug":"friendsqa-a-new-large-scale-deep-video","title":"FriendsQA: A New Large-Scale Deep Video Understanding Dataset with Fine-grained Topic Categorization for Story Videos","date":"2024-12-22","arxiv_id":"2412.17022","repositories_listed":1,"syntology":null},{"url":"/paper/expanding-performance-boundaries-of-open","slug":"expanding-performance-boundaries-of-open","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","date":"2024-12-06","arxiv_id":"2412.05271","repositories_listed":1,"syntology":{"n":9,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/expanding-performance-boundaries-of-open#ran","syntology_url":"https://syntology.ai/paper/2412.05271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05271"}},"official":{"repos":["opengvlab/internvl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/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/eyes-on-the-road-state-of-the-art-video","slug":"eyes-on-the-road-state-of-the-art-video","title":"Eyes on the Road: State-of-the-Art Video Question Answering Models Assessment for Traffic Monitoring Tasks","date":"2024-12-02","arxiv_id":"2412.01132","repositories_listed":1,"syntology":null},{"url":"/paper/videollm-knows-when-to-speak-enhancing-time","slug":"videollm-knows-when-to-speak-enhancing-time","title":"VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format","date":"2024-11-27","arxiv_id":"2411.17991","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videollm-knows-when-to-speak-enhancing-time#ran","syntology_url":"https://syntology.ai/paper/2411.17991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17991"}},"official":{"repos":["yellow-binary-tree/mmduet"],"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/videoespresso-a-large-scale-chain-of-thought","slug":"videoespresso-a-large-scale-chain-of-thought","title":"VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection","date":"2024-11-22","arxiv_id":"2411.14794","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videoespresso-a-large-scale-chain-of-thought#ran","syntology_url":"https://syntology.ai/paper/2411.14794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14794"}},"official":{"repos":["hshjerry/videoespresso"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/videgothink-assessing-egocentric-video","slug":"videgothink-assessing-egocentric-video","title":"VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI","date":"2024-10-15","arxiv_id":"2410.11623","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":9,"n_instrument":7,"n_unverified":1,"n_honours":4,"n_violates":2,"n_no_contract":3,"n_pointer_only":5,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 2 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/videgothink-assessing-egocentric-video#ran","syntology_url":"https://syntology.ai/paper/2410.11623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11623"}},"official":null}},{"url":"/paper/free-video-llm-prompt-guided-visual","slug":"free-video-llm-prompt-guided-visual","title":"Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs","date":"2024-10-14","arxiv_id":"2410.10441","repositories_listed":1,"syntology":null},{"url":"/paper/temporalbench-benchmarking-fine-grained","slug":"temporalbench-benchmarking-fine-grained","title":"TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models","date":"2024-10-14","arxiv_id":"2410.10818","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/temporalbench-benchmarking-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2410.10818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10818"}},"official":{"repos":["mu-cai/TemporalBench"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-granularity-contrastive-cross-modal","slug":"multi-granularity-contrastive-cross-modal","title":"Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question Answering","date":"2024-10-12","arxiv_id":"2410.09379","repositories_listed":1,"syntology":null},{"url":"/paper/aria-an-open-multimodal-native-mixture-of","slug":"aria-an-open-multimodal-native-mixture-of","title":"Aria: An Open Multimodal Native Mixture-of-Experts Model","date":"2024-10-08","arxiv_id":"2410.05993","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/aria-an-open-multimodal-native-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2410.05993","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05993"}},"official":{"repos":["rhymes-ai/aria"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-temporal-modeling-of-video-llms-via","slug":"enhancing-temporal-modeling-of-video-llms-via","title":"Enhancing Temporal Modeling of Video LLMs via Time Gating","date":"2024-10-08","arxiv_id":"2410.05714","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/enhancing-temporal-modeling-of-video-llms-via#ran","syntology_url":"https://syntology.ai/paper/2410.05714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05714"}},"official":{"repos":["lavi-lab/tg-vid"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/empowering-large-language-model-for-continual","slug":"empowering-large-language-model-for-continual","title":"Empowering Large Language Model for Continual Video Question Answering with Collaborative Prompting","date":"2024-10-01","arxiv_id":"2410.00771","repositories_listed":1,"syntology":null},{"url":"/paper/videoinsta-zero-shot-long-video-understanding","slug":"videoinsta-zero-shot-long-video-understanding","title":"VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs","date":"2024-09-30","arxiv_id":"2409.20365","repositories_listed":1,"syntology":null},{"url":"/paper/scene-text-grounding-for-text-based-video","slug":"scene-text-grounding-for-text-based-video","title":"Scene-Text Grounding for Text-Based Video Question Answering","date":"2024-09-22","arxiv_id":"2409.14319","repositories_listed":1,"syntology":null},{"url":"/paper/remembr-building-and-reasoning-over-long","slug":"remembr-building-and-reasoning-over-long","title":"ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation","date":"2024-09-20","arxiv_id":"2409.13682","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":3,"n_honours":3,"n_violates":0,"n_no_contract":1,"n_pointer_only":10,"phrase":"7 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/remembr-building-and-reasoning-over-long#ran","syntology_url":"https://syntology.ai/paper/2409.13682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13682"}},"official":{"repos":["NVIDIA-AI-IOT/remembr"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/oryx-mllm-on-demand-spatial-temporal","slug":"oryx-mllm-on-demand-spatial-temporal","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","date":"2024-09-19","arxiv_id":"2409.12961","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/oryx-mllm-on-demand-spatial-temporal#ran","syntology_url":"https://syntology.ai/paper/2409.12961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12961"}},"official":{"repos":["oryx-mllm/oryx"],"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"]}}},{"url":"/paper/grounded-multi-hop-videoqa-in-long-form","slug":"grounded-multi-hop-videoqa-in-long-form","title":"Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos","date":"2024-08-26","arxiv_id":"2408.14469","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/grounded-multi-hop-videoqa-in-long-form#ran","syntology_url":"https://syntology.ai/paper/2408.14469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14469"}},"official":null}}],"syntology_records":61,"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":7,"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/video-question-answering-on-next-qa","since_archive":"/sota/video-question-answering-on-next-qa#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/video-question-answering-on-mvbench","since_archive":"/sota/video-question-answering-on-mvbench#since-judged","papers_judged":5,"placed":0},{"leaderboard":"/sota/video-question-answering-on-msrvtt-qa","since_archive":"/sota/video-question-answering-on-msrvtt-qa#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":124,"papers_where_code_ran_first_page":"/task/video-question-answering/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":5,"url":"/task/video-question-answering/papers/2","json":"/task/video-question-answering/papers/2.json","rows":100},{"order":"archive","page":3,"of":5,"url":"/task/video-question-answering/papers/3","json":"/task/video-question-answering/papers/3.json","rows":100},{"order":"archive","page":4,"of":5,"url":"/task/video-question-answering/papers/4","json":"/task/video-question-answering/papers/4.json","rows":100},{"order":"archive","page":5,"of":5,"url":"/task/video-question-answering/papers/5","json":"/task/video-question-answering/papers/5.json","rows":60},{"order":"ran","page":1,"of":2,"url":"/task/video-question-answering/papers/ran/1","json":"/task/video-question-answering/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/video-question-answering/papers/ran/2","json":"/task/video-question-answering/papers/ran/2.json","rows":24}],"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":"eddd3688e66374476d76f251936f6128f58bb5d66ecd11a6f82fb236b4c3534c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}