{"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/papers/2","list_of":"/task/video-question-answering","task":"Video Question Answering","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":5,"rows_per_page":100,"rows":[101,200],"of":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":107,"every_run_a_failure_of_syntologys_instrument":17,"listed_with_a_run_with_no_instrument_failure":107,"listed_every_run_a_failure_of_syntologys_instrument":17,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/video-question-answering","prev":"/task/video-question-answering","next":"/task/video-question-answering/papers/3","papers":[{"url":"/paper/longvila-scaling-long-context-visual-language","slug":"longvila-scaling-long-context-visual-language","title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos","date":"2024-08-19","arxiv_id":"2408.10188","repositories_listed":1,"syntology":null},{"url":"/paper/mplug-owl3-towards-long-image-sequence","slug":"mplug-owl3-towards-long-image-sequence","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","date":"2024-08-09","arxiv_id":"2408.04840","repositories_listed":1,"syntology":null},{"url":"/paper/videoqa-in-the-era-of-llms-an-empirical-study","slug":"videoqa-in-the-era-of-llms-an-empirical-study","title":"VideoQA in the Era of LLMs: An Empirical Study","date":"2024-08-08","arxiv_id":"2408.04223","repositories_listed":1,"syntology":null},{"url":"/paper/2407-21757","slug":"2407-21757","title":"Learning Video Context as Interleaved Multimodal Sequences","date":"2024-07-31","arxiv_id":"2407.21757","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2407-21757#ran","syntology_url":"https://syntology.ai/paper/2407.21757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21757"}},"official":{"repos":["showlab/movieseq"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/longvideobench-a-benchmark-for-long-context","slug":"longvideobench-a-benchmark-for-long-context","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","date":"2024-07-22","arxiv_id":"2407.15754","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/longvideobench-a-benchmark-for-long-context#ran","syntology_url":"https://syntology.ai/paper/2407.15754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15754"}},"official":{"repos":["longvideobench/longvideobench"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/video-language-alignment-pre-training-via","slug":"video-language-alignment-pre-training-via","title":"Video-Language Alignment via Spatio-Temporal Graph Transformer","date":"2024-07-16","arxiv_id":"2407.11677","repositories_listed":1,"syntology":null},{"url":"/paper/meta-optimized-angular-margin-contrastive","slug":"meta-optimized-angular-margin-contrastive","title":"MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning","date":"2024-07-04","arxiv_id":"2407.03788","repositories_listed":1,"syntology":null},{"url":"/paper/internlm-xcomposer-2-5-a-versatile-large","slug":"internlm-xcomposer-2-5-a-versatile-large","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","date":"2024-07-03","arxiv_id":"2407.03320","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/internlm-xcomposer-2-5-a-versatile-large#ran","syntology_url":"https://syntology.ai/paper/2407.03320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03320"}},"official":{"repos":["internlm/internlm-xcomposer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/referring-atomic-video-action-recognition","slug":"referring-atomic-video-action-recognition","title":"Referring Atomic Video Action Recognition","date":"2024-07-02","arxiv_id":"2407.01872","repositories_listed":1,"syntology":null},{"url":"/paper/tarsier-recipes-for-training-and-evaluating-1","slug":"tarsier-recipes-for-training-and-evaluating-1","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","date":"2024-06-30","arxiv_id":"2407.00634","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tarsier-recipes-for-training-and-evaluating-1#ran","syntology_url":"https://syntology.ai/paper/2407.00634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00634"}},"official":{"repos":["bytedance/tarsier"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hcqa-ego4d-egoschema-challenge-2024","slug":"hcqa-ego4d-egoschema-challenge-2024","title":"HCQA @ Ego4D EgoSchema Challenge 2024","date":"2024-06-22","arxiv_id":"2406.15771","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hcqa-ego4d-egoschema-challenge-2024#ran","syntology_url":"https://syntology.ai/paper/2406.15771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15771"}},"official":{"repos":["hyu-zhang/hcqa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/alanavlm-a-multimodal-embodied-ai-foundation","slug":"alanavlm-a-multimodal-embodied-ai-foundation","title":"AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding","date":"2024-06-19","arxiv_id":"2406.13807","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/alanavlm-a-multimodal-embodied-ai-foundation#ran","syntology_url":"https://syntology.ai/paper/2406.13807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13807"}},"official":{"repos":["alanaai/evud"],"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/voco-llama-towards-vision-compression-with","slug":"voco-llama-towards-vision-compression-with","title":"VoCo-LLaMA: Towards Vision Compression with Large Language Models","date":"2024-06-18","arxiv_id":"2406.12275","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":5,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/voco-llama-towards-vision-compression-with#ran","syntology_url":"https://syntology.ai/paper/2406.12275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12275"}},"official":{"repos":["Yxxxb/VoCo-LLaMA"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/task-me-anything","slug":"task-me-anything","title":"Task Me Anything","date":"2024-06-17","arxiv_id":"2406.11775","repositories_listed":1,"syntology":null},{"url":"/paper/too-many-frames-not-all-useful-efficient","slug":"too-many-frames-not-all-useful-efficient","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","date":"2024-06-13","arxiv_id":"2406.09396","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/too-many-frames-not-all-useful-efficient#ran","syntology_url":"https://syntology.ai/paper/2406.09396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09396"}},"official":{"repos":["jongwoopark7978/LVNet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/videogpt-integrating-image-and-video-encoders","slug":"videogpt-integrating-image-and-video-encoders","title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","date":"2024-06-13","arxiv_id":"2406.09418","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/videogpt-integrating-image-and-video-encoders#ran","syntology_url":"https://syntology.ai/paper/2406.09418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09418"}},"official":{"repos":["mbzuai-oryx/videogpt-plus"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/flash-vstream-memory-based-real-time","slug":"flash-vstream-memory-based-real-time","title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","date":"2024-06-12","arxiv_id":"2406.08085","repositories_listed":1,"syntology":null},{"url":"/paper/compositional-4d-dynamic-scenes-understanding","slug":"compositional-4d-dynamic-scenes-understanding","title":"Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering","date":"2024-06-02","arxiv_id":"2406.00622","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 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) · 1 unverified","sample_list":"/paper/compositional-4d-dynamic-scenes-understanding#ran","syntology_url":"https://syntology.ai/paper/2406.00622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00622"}},"official":{"repos":["XingruiWang/SuperCLEVR-Physics"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/encoding-and-controlling-global-semantics-for","slug":"encoding-and-controlling-global-semantics-for","title":"Encoding and Controlling Global Semantics for Long-form Video Question Answering","date":"2024-05-30","arxiv_id":"2405.19723","repositories_listed":1,"syntology":null},{"url":"/paper/freeva-offline-mllm-as-training-free-video","slug":"freeva-offline-mllm-as-training-free-video","title":"FreeVA: Offline MLLM as Training-Free Video Assistant","date":"2024-05-13","arxiv_id":"2405.07798","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/freeva-offline-mllm-as-training-free-video#ran","syntology_url":"https://syntology.ai/paper/2405.07798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.07798"}},"official":{"repos":["whwu95/freeva"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/moviechat-question-aware-sparse-memory-for","slug":"moviechat-question-aware-sparse-memory-for","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","date":"2024-04-26","arxiv_id":"2404.17176","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":3,"n_honours":2,"n_violates":1,"n_no_contract":4,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/moviechat-question-aware-sparse-memory-for#ran","syntology_url":"https://syntology.ai/paper/2404.17176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.17176"}},"official":{"repos":["rese1f/MovieChat"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/pllava-parameter-free-llava-extension-from-1","slug":"pllava-parameter-free-llava-extension-from-1","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","date":"2024-04-25","arxiv_id":"2404.16994","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/pllava-parameter-free-llava-extension-from-1#ran","syntology_url":"https://syntology.ai/paper/2404.16994","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16994"}},"official":{"repos":["magic-research/PLLaVA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/listen-then-see-video-alignment-with-speaker","slug":"listen-then-see-video-alignment-with-speaker","title":"Listen Then See: Video Alignment with Speaker Attention","date":"2024-04-21","arxiv_id":"2404.13530","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-localize-objects-improves-spatial","slug":"learning-to-localize-objects-improves-spatial","title":"Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs","date":"2024-04-11","arxiv_id":"2404.07449","repositories_listed":1,"syntology":null},{"url":"/paper/ma-lmm-memory-augmented-large-multimodal","slug":"ma-lmm-memory-augmented-large-multimodal","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","date":"2024-04-08","arxiv_id":"2404.05726","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ma-lmm-memory-augmented-large-multimodal#ran","syntology_url":"https://syntology.ai/paper/2404.05726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05726"}},"official":{"repos":["boheumd/MA-LMM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/longvlm-efficient-long-video-understanding","slug":"longvlm-efficient-long-video-understanding","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","date":"2024-04-04","arxiv_id":"2404.03384","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"0 ran · 4 unverified","sample_list":"/paper/longvlm-efficient-long-video-understanding#ran","syntology_url":"https://syntology.ai/paper/2404.03384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03384"}},"official":{"repos":["ziplab/longvlm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/causalchaos-dataset-for-comprehensive-causal","slug":"causalchaos-dataset-for-comprehensive-causal","title":"CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes","date":"2024-04-01","arxiv_id":"2404.01299","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/causalchaos-dataset-for-comprehensive-causal#ran","syntology_url":"https://syntology.ai/paper/2404.01299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01299"}},"official":{"repos":["lunaproject22/causalchaos"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/direct-preference-optimization-of-video-large","slug":"direct-preference-optimization-of-video-large","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward","date":"2024-04-01","arxiv_id":"2404.01258","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":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/direct-preference-optimization-of-video-large#ran","syntology_url":"https://syntology.ai/paper/2404.01258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01258"}},"official":{"repos":["riflezhang/llava-hound-dpo"],"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/traveler-a-multi-lmm-agent-framework-for","slug":"traveler-a-multi-lmm-agent-framework-for","title":"TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering","date":"2024-04-01","arxiv_id":"2404.01476","repositories_listed":1,"syntology":null},{"url":"/paper/st-llm-large-language-models-are-effective-1","slug":"st-llm-large-language-models-are-effective-1","title":"ST-LLM: Large Language Models Are Effective Temporal Learners","date":"2024-03-30","arxiv_id":"2404.00308","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/st-llm-large-language-models-are-effective-1#ran","syntology_url":"https://syntology.ai/paper/2404.00308","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00308"}},"official":{"repos":["TencentARC/ST-LLM"],"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","unlocated"]}}},{"url":"/paper/an-image-grid-can-be-worth-a-video-zero-shot","slug":"an-image-grid-can-be-worth-a-video-zero-shot","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","date":"2024-03-27","arxiv_id":"2403.18406","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-image-grid-can-be-worth-a-video-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2403.18406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18406"}},"official":{"repos":["imagegridworth/IG-VLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lita-language-instructed-temporal","slug":"lita-language-instructed-temporal","title":"LITA: Language Instructed Temporal-Localization Assistant","date":"2024-03-27","arxiv_id":"2403.19046","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/lita-language-instructed-temporal#ran","syntology_url":"https://syntology.ai/paper/2403.19046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19046"}},"official":{"repos":["nvlabs/lita"],"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/omnivid-a-generative-framework-for-universal","slug":"omnivid-a-generative-framework-for-universal","title":"OmniVid: A Generative Framework for Universal Video Understanding","date":"2024-03-26","arxiv_id":"2403.17935","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/omnivid-a-generative-framework-for-universal#ran","syntology_url":"https://syntology.ai/paper/2403.17935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17935"}},"official":{"repos":["wangjk666/omnivid"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/elysium-exploring-object-level-perception-in","slug":"elysium-exploring-object-level-perception-in","title":"Elysium: Exploring Object-level Perception in Videos via MLLM","date":"2024-03-25","arxiv_id":"2403.16558","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/elysium-exploring-object-level-perception-in#ran","syntology_url":"https://syntology.ai/paper/2403.16558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16558"}},"official":{"repos":["hon-wong/elysium"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vid-tldr-training-free-token-merging-for","slug":"vid-tldr-training-free-token-merging-for","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","date":"2024-03-20","arxiv_id":"2403.13347","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vid-tldr-training-free-token-merging-for#ran","syntology_url":"https://syntology.ai/paper/2403.13347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13347"}},"official":{"repos":["mlvlab/vid-tldr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hawkeye-training-video-text-llms-for","slug":"hawkeye-training-video-text-llms-for","title":"HawkEye: Training Video-Text LLMs for Grounding Text in Videos","date":"2024-03-15","arxiv_id":"2403.10228","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":6,"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/hawkeye-training-video-text-llms-for#ran","syntology_url":"https://syntology.ai/paper/2403.10228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10228"}},"official":{"repos":["yellow-binary-tree/hawkeye"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dam-dynamic-adapter-merging-for-continual","slug":"dam-dynamic-adapter-merging-for-continual","title":"DAM: Dynamic Adapter Merging for Continual Video QA Learning","date":"2024-03-13","arxiv_id":"2403.08755","repositories_listed":1,"syntology":null},{"url":"/paper/gemini-1-5-unlocking-multimodal-understanding","slug":"gemini-1-5-unlocking-multimodal-understanding","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","date":"2024-03-08","arxiv_id":"2403.05530","repositories_listed":1,"syntology":null},{"url":"/paper/question-instructed-visual-descriptions-for","slug":"question-instructed-visual-descriptions-for","title":"Question-Instructed Visual Descriptions for Zero-Shot Video Question Answering","date":"2024-02-16","arxiv_id":"2402.10698","repositories_listed":1,"syntology":null},{"url":"/paper/crema-multimodal-compositional-video","slug":"crema-multimodal-compositional-video","title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion","date":"2024-02-08","arxiv_id":"2402.05889","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"8 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; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/crema-multimodal-compositional-video#ran","syntology_url":"https://syntology.ai/paper/2402.05889","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05889"}},"official":{"repos":["Yui010206/CREMA"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sphinx-x-scaling-data-and-parameters-for-a","slug":"sphinx-x-scaling-data-and-parameters-for-a","title":"SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models","date":"2024-02-08","arxiv_id":"2402.05935","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sphinx-x-scaling-data-and-parameters-for-a#ran","syntology_url":"https://syntology.ai/paper/2402.05935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05935"}},"official":{"repos":["alpha-vllm/llama2-accessory"],"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/ytcommentqa-video-question-answerability-in","slug":"ytcommentqa-video-question-answerability-in","title":"YTCommentQA: Video Question Answerability in Instructional Videos","date":"2024-01-30","arxiv_id":"2401.17343","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-gaussian-contrastive","slug":"weakly-supervised-gaussian-contrastive","title":"Weakly Supervised Gaussian Contrastive Grounding with Large Multimodal Models for Video Question Answering","date":"2024-01-19","arxiv_id":"2401.10711","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/weakly-supervised-gaussian-contrastive#ran","syntology_url":"https://syntology.ai/paper/2401.10711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10711"}},"official":{"repos":["whb139426/gcg"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/stair-spatial-temporal-reasoning-with","slug":"stair-spatial-temporal-reasoning-with","title":"STAIR: Spatial-Temporal Reasoning with Auditable Intermediate Results for Video Question Answering","date":"2024-01-08","arxiv_id":"2401.03901","repositories_listed":1,"syntology":null},{"url":"/paper/glance-and-focus-memory-prompting-for-multi-1","slug":"glance-and-focus-memory-prompting-for-multi-1","title":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering","date":"2024-01-03","arxiv_id":"2401.01529","repositories_listed":1,"syntology":{"n":18,"n_ran":14,"n_constructed":2,"n_ran_checked":14,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":13,"n_pointer_only":7,"phrase":"14 ran (of which 2 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 1 violated, 13 with no contract checked; 0 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":14,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/sports-qa-a-large-scale-video-question","slug":"sports-qa-a-large-scale-video-question","title":"Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports","date":"2024-01-03","arxiv_id":"2401.01505","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-llm-framework-for-long-range-video","slug":"a-simple-llm-framework-for-long-range-video","title":"A Simple LLM Framework for Long-Range Video Question-Answering","date":"2023-12-28","arxiv_id":"2312.17235","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-simple-llm-framework-for-long-range-video#ran","syntology_url":"https://syntology.ai/paper/2312.17235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17235"}},"official":{"repos":["ceezh/llovi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/shot2story20k-a-new-benchmark-for","slug":"shot2story20k-a-new-benchmark-for","title":"Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos","date":"2023-12-16","arxiv_id":"2312.10300","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/shot2story20k-a-new-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2312.10300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10300"}},"official":{"repos":["bytedance/Shot2Story"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vlap-efficient-video-language-alignment-via","slug":"vlap-efficient-video-language-alignment-via","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","date":"2023-12-13","arxiv_id":"2312.08367","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/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":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/grounded-question-answering-in-long","slug":"grounded-question-answering-in-long","title":"Grounded Question-Answering in Long Egocentric Videos","date":"2023-12-11","arxiv_id":"2312.06505","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/grounded-question-answering-in-long#ran","syntology_url":"https://syntology.ai/paper/2312.06505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06505"}},"official":{"repos":["becomebright/groundvqa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vtimellm-empower-llm-to-grasp-video-moments","slug":"vtimellm-empower-llm-to-grasp-video-moments","title":"VTimeLLM: Empower LLM to Grasp Video Moments","date":"2023-11-30","arxiv_id":"2311.18445","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":11,"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) · 4 unverified","sample_list":"/paper/vtimellm-empower-llm-to-grasp-video-moments#ran","syntology_url":"https://syntology.ai/paper/2311.18445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18445"}},"official":{"repos":["huangb23/vtimellm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/autoeval-video-an-automatic-benchmark-for","slug":"autoeval-video-an-automatic-benchmark-for","title":"AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering","date":"2023-11-25","arxiv_id":"2311.14906","repositories_listed":1,"syntology":null},{"url":"/paper/vamos-versatile-action-models-for-video","slug":"vamos-versatile-action-models-for-video","title":"Vamos: Versatile Action Models for Video Understanding","date":"2023-11-22","arxiv_id":"2311.13627","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vamos-versatile-action-models-for-video#ran","syntology_url":"https://syntology.ai/paper/2311.13627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13627"}},"official":{"repos":["brown-palm/Vamos"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/videocon-robust-video-language-alignment-via","slug":"videocon-robust-video-language-alignment-via","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","date":"2023-11-15","arxiv_id":"2311.10111","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/videocon-robust-video-language-alignment-via#ran","syntology_url":"https://syntology.ai/paper/2311.10111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.10111"}},"official":{"repos":["hritikbansal/videocon"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/acquired-a-dataset-for-answering","slug":"acquired-a-dataset-for-answering","title":"ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos","date":"2023-11-02","arxiv_id":"2311.01620","repositories_listed":1,"syntology":null},{"url":"/paper/long-story-short-a-summarize-then-search","slug":"long-story-short-a-summarize-then-search","title":"Long Story Short: a Summarize-then-Search Method for Long Video Question Answering","date":"2023-11-02","arxiv_id":"2311.01233","repositories_listed":1,"syntology":null},{"url":"/paper/harvest-video-foundation-models-via-efficient","slug":"harvest-video-foundation-models-via-efficient","title":"Harvest Video Foundation Models via Efficient Post-Pretraining","date":"2023-10-30","arxiv_id":"2310.19554","repositories_listed":1,"syntology":null},{"url":"/paper/testa-temporal-spatial-token-aggregation-for","slug":"testa-temporal-spatial-token-aggregation-for","title":"TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding","date":"2023-10-29","arxiv_id":"2310.19060","repositories_listed":1,"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":5,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/testa-temporal-spatial-token-aggregation-for#ran","syntology_url":"https://syntology.ai/paper/2310.19060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19060"}},"official":{"repos":["renshuhuai-andy/testa"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-are-temporal-and-causal","slug":"large-language-models-are-temporal-and-causal","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","date":"2023-10-24","arxiv_id":"2310.15747","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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":[]}}},{"url":"/paper/analyzing-zero-shot-abilities-of-vision","slug":"analyzing-zero-shot-abilities-of-vision","title":"Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks","date":"2023-10-07","arxiv_id":"2310.04914","repositories_listed":1,"syntology":null},{"url":"/paper/anymal-an-efficient-and-scalable-any-modality","slug":"anymal-an-efficient-and-scalable-any-modality","title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model","date":"2023-09-27","arxiv_id":"2309.16058","repositories_listed":1,"syntology":null},{"url":"/paper/one-for-all-video-conversation-is-feasible","slug":"one-for-all-video-conversation-is-feasible","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","date":"2023-09-27","arxiv_id":"2309.15785","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/one-for-all-video-conversation-is-feasible#ran","syntology_url":"https://syntology.ai/paper/2309.15785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15785"}},"official":{"repos":["farewellthree/BT-Adapter"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-and-few-shot-video-question","slug":"zero-shot-and-few-shot-video-question","title":"Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts","date":"2023-09-27","arxiv_id":"2309.15915","repositories_listed":1,"syntology":null},{"url":"/paper/can-i-trust-your-answer-visually-grounded","slug":"can-i-trust-your-answer-visually-grounded","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","date":"2023-09-04","arxiv_id":"2309.01327","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/can-i-trust-your-answer-visually-grounded#ran","syntology_url":"https://syntology.ai/paper/2309.01327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.01327"}},"official":{"repos":["doc-doc/next-gqa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/open-vocabulary-video-question-answering-a","slug":"open-vocabulary-video-question-answering-a","title":"Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models","date":"2023-08-18","arxiv_id":"2308.09363","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/open-vocabulary-video-question-answering-a#ran","syntology_url":"https://syntology.ai/paper/2308.09363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09363"}},"official":{"repos":["mlvlab/ovqa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/vl-pet-vision-and-language-parameter","slug":"vl-pet-vision-and-language-parameter","title":"VL-PET: Vision-and-Language Parameter-Efficient Tuning via Granularity Control","date":"2023-08-18","arxiv_id":"2308.09804","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vl-pet-vision-and-language-parameter#ran","syntology_url":"https://syntology.ai/paper/2308.09804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09804"}},"official":{"repos":["henryhzy/vl-pet"],"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/egoschema-a-diagnostic-benchmark-for-very-1","slug":"egoschema-a-diagnostic-benchmark-for-very-1","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","date":"2023-08-17","arxiv_id":"2308.09126","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/egoschema-a-diagnostic-benchmark-for-very-1#ran","syntology_url":"https://syntology.ai/paper/2308.09126","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09126"}},"official":{"repos":["egoschema/egoschema"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tem-adapter-adapting-image-text-pretraining","slug":"tem-adapter-adapting-image-text-pretraining","title":"Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer","date":"2023-08-16","arxiv_id":"2308.08414","repositories_listed":1,"syntology":null},{"url":"/paper/moviechat-from-dense-token-to-sparse-memory","slug":"moviechat-from-dense-token-to-sparse-memory","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","date":"2023-07-31","arxiv_id":"2307.16449","repositories_listed":1,"syntology":null},{"url":"/paper/discovering-spatio-temporal-rationales-for","slug":"discovering-spatio-temporal-rationales-for","title":"Discovering Spatio-Temporal Rationales for Video Question Answering","date":"2023-07-22","arxiv_id":"2307.12058","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"6 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/discovering-spatio-temporal-rationales-for#ran","syntology_url":"https://syntology.ai/paper/2307.12058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12058"}},"official":{"repos":["yl3800/transtr"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/reading-between-the-lanes-text-videoqa-on-the","slug":"reading-between-the-lanes-text-videoqa-on-the","title":"Reading Between the Lanes: Text VideoQA on the Road","date":"2023-07-08","arxiv_id":"2307.03948","repositories_listed":1,"syntology":null},{"url":"/paper/lightweight-recurrent-cross-modal-encoder-for","slug":"lightweight-recurrent-cross-modal-encoder-for","title":"Lightweight Recurrent Cross-modal Encoder for Video Question Answering","date":"2023-06-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/funqa-towards-surprising-video-comprehension","slug":"funqa-towards-surprising-video-comprehension","title":"FunQA: Towards Surprising Video Comprehension","date":"2023-06-26","arxiv_id":"2306.14899","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/funqa-towards-surprising-video-comprehension#ran","syntology_url":"https://syntology.ai/paper/2306.14899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.14899"}},"official":{"repos":["jingkang50/funqa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cosa-concatenated-sample-pretrained-vision","slug":"cosa-concatenated-sample-pretrained-vision","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","date":"2023-06-15","arxiv_id":"2306.09085","repositories_listed":1,"syntology":null},{"url":"/paper/perception-test-a-diagnostic-benchmark-for-2","slug":"perception-test-a-diagnostic-benchmark-for-2","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","date":"2023-05-23","arxiv_id":"2305.13786","repositories_listed":1,"syntology":null},{"url":"/paper/paxion-patching-action-knowledge-in-video-1","slug":"paxion-patching-action-knowledge-in-video-1","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","date":"2023-05-18","arxiv_id":"2305.10683","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/paxion-patching-action-knowledge-in-video-1#ran","syntology_url":"https://syntology.ai/paper/2305.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10683"}},"official":{"repos":["mikewangwzhl/paxion"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/self-chained-image-language-model-for-video-1","slug":"self-chained-image-language-model-for-video-1","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","date":"2023-05-11","arxiv_id":"2305.06988","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/self-chained-image-language-model-for-video-1#ran","syntology_url":"https://syntology.ai/paper/2305.06988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.06988"}},"official":{"repos":["yui010206/sevila"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/videochat-chat-centric-video-understanding","slug":"videochat-chat-centric-video-understanding","title":"VideoChat: Chat-Centric Video Understanding","date":"2023-05-10","arxiv_id":"2305.06355","repositories_listed":1,"syntology":null},{"url":"/paper/anetqa-a-large-scale-benchmark-for-fine","slug":"anetqa-a-large-scale-benchmark-for-fine","title":"ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos","date":"2023-05-04","arxiv_id":"2305.02519","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/anetqa-a-large-scale-benchmark-for-fine#ran","syntology_url":"https://syntology.ai/paper/2305.02519","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.02519"}},"official":{"repos":["MILVLG/anetqa-code"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-situation-hyper-graphs-for-video","slug":"learning-situation-hyper-graphs-for-video","title":"Learning Situation Hyper-Graphs for Video Question Answering","date":"2023-04-18","arxiv_id":"2304.08682","repositories_listed":1,"syntology":{"n":15,"n_ran":8,"n_constructed":5,"n_ran_checked":8,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":15,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/learning-situation-hyper-graphs-for-video#ran","syntology_url":"https://syntology.ai/paper/2304.08682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08682"}},"official":{"repos":["aurooj/shg-vqa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":5,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/svitt-temporal-learning-of-sparse-video-text","slug":"svitt-temporal-learning-of-sparse-video-text","title":"SViTT: Temporal Learning of Sparse Video-Text Transformers","date":"2023-04-18","arxiv_id":"2304.08809","repositories_listed":1,"syntology":null},{"url":"/paper/valor-vision-audio-language-omni-perception","slug":"valor-vision-audio-language-omni-perception","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","date":"2023-04-17","arxiv_id":"2304.08345","repositories_listed":1,"syntology":null},{"url":"/paper/verbs-in-action-improving-verb-understanding","slug":"verbs-in-action-improving-verb-understanding","title":"Verbs in Action: Improving verb understanding in video-language models","date":"2023-04-13","arxiv_id":"2304.06708","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/verbs-in-action-improving-verb-understanding#ran","syntology_url":"https://syntology.ai/paper/2304.06708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.06708"}},"official":{"repos":["google-research/scenic"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mammut-a-simple-architecture-for-joint","slug":"mammut-a-simple-architecture-for-joint","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","date":"2023-03-29","arxiv_id":"2303.16839","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mammut-a-simple-architecture-for-joint#ran","syntology_url":"https://syntology.ai/paper/2303.16839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16839"}},"official":null}},{"url":"/paper/unmasked-teacher-towards-training-efficient","slug":"unmasked-teacher-towards-training-efficient","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","date":"2023-03-28","arxiv_id":"2303.16058","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unmasked-teacher-towards-training-efficient#ran","syntology_url":"https://syntology.ai/paper/2303.16058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16058"}},"official":{"repos":["opengvlab/unmasked_teacher"],"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":["official"]}}},{"url":"/paper/meltr-meta-loss-transformer-for-learning-to","slug":"meltr-meta-loss-transformer-for-learning-to","title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","date":"2023-03-23","arxiv_id":"2303.13009","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/meltr-meta-loss-transformer-for-learning-to#ran","syntology_url":"https://syntology.ai/paper/2303.13009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13009"}},"official":{"repos":["mlvlab/MELTR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vipergpt-visual-inference-via-python","slug":"vipergpt-visual-inference-via-python","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","date":"2023-03-14","arxiv_id":"2303.08128","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-video-question-answering-via","slug":"contrastive-video-question-answering-via","title":"Contrastive Video Question Answering via Video Graph Transformer","date":"2023-02-27","arxiv_id":"2302.13668","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/contrastive-video-question-answering-via#ran","syntology_url":"https://syntology.ai/paper/2302.13668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13668"}},"official":{"repos":["doc-doc/covgt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/connecting-vision-and-language-with-video","slug":"connecting-vision-and-language-with-video","title":"Connecting Vision and Language with Video Localized Narratives","date":"2023-02-22","arxiv_id":"2302.11217","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/connecting-vision-and-language-with-video#ran","syntology_url":"https://syntology.ai/paper/2302.11217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11217"}},"official":{"repos":["google/video-localized-narratives"],"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/efficient-end-to-end-video-question-answering","slug":"efficient-end-to-end-video-question-answering","title":"Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer","date":"2023-02-04","arxiv_id":"2302.02136","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-temporal-concurrency-for-video","slug":"exploring-temporal-concurrency-for-video","title":"Exploring Temporal Concurrency for Video-Language Representation Learning","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/intentqa-context-aware-video-intent-reasoning","slug":"intentqa-context-aware-video-intent-reasoning","title":"IntentQA: Context-aware Video Intent Reasoning","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mist-multi-modal-iterative-spatial-temporal","slug":"mist-multi-modal-iterative-spatial-temporal","title":"MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering","date":"2022-12-19","arxiv_id":"2212.09522","repositories_listed":1,"syntology":null},{"url":"/paper/vindlu-a-recipe-for-effective-video-and","slug":"vindlu-a-recipe-for-effective-video-and","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","date":"2022-12-09","arxiv_id":"2212.05051","repositories_listed":1,"syntology":null},{"url":"/paper/visual-commonsense-aware-representation","slug":"visual-commonsense-aware-representation","title":"Visual Commonsense-aware Representation Network for Video Captioning","date":"2022-11-17","arxiv_id":"2211.09469","repositories_listed":1,"syntology":null},{"url":"/paper/cripp-vqa-counterfactual-reasoning-about","slug":"cripp-vqa-counterfactual-reasoning-about","title":"CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering","date":"2022-11-07","arxiv_id":"2211.03779","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cripp-vqa-counterfactual-reasoning-about#ran","syntology_url":"https://syntology.ai/paper/2211.03779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03779"}},"official":{"repos":["maitreyapatel/cripp-vqa"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/perception-test-a-diagnostic-benchmark-for","slug":"perception-test-a-diagnostic-benchmark-for","title":"Perception Test: A Diagnostic Benchmark for Multimodal Models","date":"2022-10-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vision-language-pre-training-basics-recent","slug":"vision-language-pre-training-basics-recent","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","date":"2022-10-17","arxiv_id":"2210.09263","repositories_listed":1,"syntology":null},{"url":"/paper/video-in-10-bits-few-bit-videoqa-for","slug":"video-in-10-bits-few-bit-videoqa-for","title":"Video in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy","date":"2022-10-15","arxiv_id":"2210.08391","repositories_listed":1,"syntology":null},{"url":"/paper/long-form-video-language-pre-training-with","slug":"long-form-video-language-pre-training-with","title":"Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning","date":"2022-10-12","arxiv_id":"2210.06031","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/long-form-video-language-pre-training-with#ran","syntology_url":"https://syntology.ai/paper/2210.06031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06031"}},"official":{"repos":["microsoft/xpretrain"],"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"]}}}],"record_sha256":"38b53cf50bc53e05fcf256e3bb0be5ba3d7540bc7d1fe918b8c5fbdc4a1badb4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}