{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","arxiv_id":"2305.18500","date":"2023-05-29","proceeding":"NeurIPS 2023 11","authors":["Sihan Chen","Handong Li","Qunbo Wang","Zijia Zhao","Mingzhen Sun","Xinxin Zhu","Jing Liu"],"abstract":"Vision and text have been fully explored in contemporary video-text foundational models, while other modalities such as audio and subtitles in videos have not received sufficient attention. In this paper, we resort to establish connections between multi-modality video tracks, including Vision, Audio, and Subtitle, and Text by exploring an automatically generated large-scale omni-modality video caption dataset called VAST-27M. Specifically, we first collect 27 million open-domain video clips and separately train a vision and an audio captioner to generate vision and audio captions. Then, we employ an off-the-shelf Large Language Model (LLM) to integrate the generated captions, together with subtitles and instructional prompts into omni-modality captions. Based on the proposed VAST-27M dataset, we train an omni-modality video-text foundational model named VAST, which can perceive and process vision, audio, and subtitle modalities from video, and better support various tasks including vision-text, audio-text, and multi-modal video-text tasks (retrieval, captioning and QA). Extensive experiments have been conducted to demonstrate the effectiveness of our proposed VAST-27M corpus and VAST foundation model. VAST achieves 22 new state-of-the-art results on various cross-modality benchmarks. Code, model and dataset will be released at https://github.com/TXH-mercury/VAST.","url_abs":"https://arxiv.org/abs/2305.18500v2","url_pdf":"https://arxiv.org/pdf/2305.18500v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"vast-a-vision-audio-subtitle-text-omni-1","repo_url":"https://github.com/txh-mercury/vast","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"vast-a-vision-audio-subtitle-text-omni-1","repo_url":"https://github.com/TXH-mercury/VALOR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-captioning","task_name":"Audio captioning"},{"task_slug":null,"task_name":"Audio-Visual Captioning"},{"task_slug":"audio-visual-question-answering","task_name":"Audio-visual Question Answering"},{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"tgif-frame","task_name":"TGIF-Frame"},{"task_slug":"text-to-audio-retrieval","task_name":"Text to Audio Retrieval"},{"task_slug":"video-captioning","task_name":"Video Captioning"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"zero-shot-cross-modal-retrieval","task_name":"Zero-Shot Cross-Modal Retrieval"},{"task_slug":"zero-shot-video-retrieval","task_name":"Zero-Shot Video Retrieval"},{"task_slug":null,"task_name":"text-to-audiovisual retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-captioning-on-audiocaps","task":"Audio captioning","dataset":"AudioCaps","model":"VAST","rank_in_archive_order":17,"of":18,"metrics":{"BLEU-4":"0.295","CIDEr":"0.781","METEOR":"0.247","ROUGE-L":"0.509"},"uses_additional_data":true},{"leaderboard":"/sota/audio-captioning-on-clotho","task":"Audio captioning","dataset":"Clotho","model":"VAST","rank_in_archive_order":9,"of":11,"metrics":{"BLEU-4":"19","CIDEr":"0.519","METEOR":"19.3","ROUGE-L":"40.8"},"uses_additional_data":true},{"leaderboard":"/sota/audio-visual-question-answering-on-music-avqa","task":"Audio-visual Question Answering","dataset":"MUSIC-AVQA","model":"VAST","rank_in_archive_order":1,"of":6,"metrics":{"Acc":"80.7"},"uses_additional_data":true},{"leaderboard":"/sota/cross-modal-retrieval-on-coco-2014","task":"Cross-Modal Retrieval","dataset":"COCO 2014","model":"VAST","rank_in_archive_order":1,"of":36,"metrics":{"Text-to-image R@1":"68.0","Text-to-image R@10":"92.8","Text-to-image R@5":"87.7"},"uses_additional_data":true},{"leaderboard":"/sota/cross-modal-retrieval-on-flickr30k","task":"Cross-Modal Retrieval","dataset":"Flickr30k","model":"VAST","rank_in_archive_order":27,"of":27,"metrics":{"Text-to-image R@1":"91.0","Text-to-image R@10":"99.5","Text-to-image R@5":"98.5"},"uses_additional_data":true},{"leaderboard":"/sota/image-captioning-on-coco-captions","task":"Image Captioning","dataset":"COCO Captions","model":"VAST","rank_in_archive_order":37,"of":41,"metrics":{"CIDER":"149.0","SPICE":"27.0"},"uses_additional_data":true},{"leaderboard":"/sota/text-to-audio-retrieval-on-audiocaps","task":"Text to Audio Retrieval","dataset":"AudioCaps","model":"VAST","rank_in_archive_order":2,"of":11,"metrics":{"R@1":"52.0","R@10":"82.9","R@5":"76.8"},"uses_additional_data":true},{"leaderboard":"/sota/text-to-audio-retrieval-on-clotho","task":"Text to Audio Retrieval","dataset":"Clotho","model":"VAST","rank_in_archive_order":3,"of":12,"metrics":{"R@1":"26.9","R@10":"66.1","R@5":"53.2"},"uses_additional_data":true},{"leaderboard":"/sota/video-captioning-on-msr-vtt-1","task":"Video Captioning","dataset":"MSR-VTT","model":"VAST","rank_in_archive_order":2,"of":24,"metrics":{"BLEU-4":"56.7","CIDEr":"78.0"},"uses_additional_data":true},{"leaderboard":"/sota/video-captioning-on-tvc","task":"Video Captioning","dataset":"TVC","model":"VAST","rank_in_archive_order":1,"of":2,"metrics":{"BLEU-4":"19.9","CIDEr":"74.1"},"uses_additional_data":true},{"leaderboard":"/sota/video-captioning-on-vatex-1","task":"Video Captioning","dataset":"VATEX","model":"VAST","rank_in_archive_order":2,"of":10,"metrics":{"BLEU-4":"45.0","CIDEr":"99.5"},"uses_additional_data":true},{"leaderboard":"/sota/video-captioning-on-youcook2","task":"Video Captioning","dataset":"YouCook2","model":"VAST","rank_in_archive_order":1,"of":14,"metrics":{"BLEU-4":"18.2","CIDEr":"1.99"},"uses_additional_data":true},{"leaderboard":"/sota/video-question-answering-on-activitynet-qa","task":"Video Question Answering","dataset":"ActivityNet-QA","model":"VAST","rank_in_archive_order":5,"of":36,"metrics":{"Accuracy":"50.4"},"uses_additional_data":true},{"leaderboard":"/sota/video-question-answering-on-msrvtt-qa","task":"Video Question Answering","dataset":"MSRVTT-QA","model":"VAST","rank_in_archive_order":2,"of":14,"metrics":{"Accuracy":"50.1"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-activitynet","task":"Video Retrieval","dataset":"ActivityNet","model":"VAST","rank_in_archive_order":2,"of":31,"metrics":{"text-to-video R@1":"70.5","text-to-video R@10":"95.5","text-to-video R@5":"90.9"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-didemo","task":"Video Retrieval","dataset":"DiDeMo","model":"VAST","rank_in_archive_order":3,"of":40,"metrics":{"text-to-video R@1":"72.0","text-to-video R@10":"91.4","text-to-video R@5":"89.0"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-msr-vtt","task":"Video Retrieval","dataset":"MSR-VTT","model":"VAST","rank_in_archive_order":2,"of":40,"metrics":{"text-to-video R@1":"63.9","text-to-video R@10":"89.6","text-to-video R@5":"84.3"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-vatex","task":"Video Retrieval","dataset":"VATEX","model":"VAST","rank_in_archive_order":2,"of":13,"metrics":{"text-to-video R@1":"83.0","text-to-video R@10":"99.2","text-to-video R@5":"98.2"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-youcook2","task":"Video Retrieval","dataset":"YouCook2","model":"VAST","rank_in_archive_order":1,"of":16,"metrics":{"text-to-video R@1":"50.4","text-to-video R@10":"80.8","text-to-video R@5":"74.3"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-on-msvd-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSVD-QA","model":"VAST","rank_in_archive_order":5,"of":36,"metrics":{"Accuracy":"0.60"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-cross-modal-retrieval-on-flickr30k","task":"Zero-Shot Cross-Modal Retrieval","dataset":"Flickr30k","model":"VAST","rank_in_archive_order":22,"of":22,"metrics":{"Text-to-image R@1":"90.4"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-video-retrieval-on-didemo","task":"Zero-Shot Video Retrieval","dataset":"DiDeMo","model":"VAST","rank_in_archive_order":3,"of":26,"metrics":{"text-to-video R@1":"55.5","text-to-video R@10":"79.6","text-to-video R@5":"74.3"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-video-retrieval-on-msr-vtt","task":"Zero-Shot Video Retrieval","dataset":"MSR-VTT","model":"VAST","rank_in_archive_order":6,"of":41,"metrics":{"text-to-video R@1":"49.3","text-to-video R@10":"73.9","text-to-video R@5":"68.3"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.18500","atlas_url":"https://app.syntology.ai/?focus=2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/TXH-mercury/VAST","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TXH-mercury/VALOR","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/txh-mercury/vast","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":5,"ran":6,"ran_violates":1,"ran_fixture":1,"ran_honours":2,"unverified":27},"by_repo_kind":{"official":{"samples":19,"ran":6,"repositories":1},"listed":{"samples":23,"ran":9,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"0f786c407fb1ee4c","entry":"swish","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/bert.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/bert.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f786c407fb1ee4c"}},{"code_sha256_prefix":"d0dc6ea5061f7dc5","entry":"Contra_head","repo":"txh-mercury/vast","repo_kind":"official","path":"model/vast.py","file_url":"https://github.com/txh-mercury/vast/blob/HEAD/model/vast.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d0dc6ea5061f7dc5"}},{"code_sha256_prefix":"48d525c2e5cbc84a","entry":"GELU","repo":"txh-mercury/vast","repo_kind":"official","path":"model/vast.py","file_url":"https://github.com/txh-mercury/vast/blob/HEAD/model/vast.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"48d525c2e5cbc84a"}},{"code_sha256_prefix":"a839c0c942f1b694","entry":"GatherLayer","repo":"txh-mercury/vast","repo_kind":"official","path":"model/vast.py","file_url":"https://github.com/txh-mercury/vast/blob/HEAD/model/vast.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a839c0c942f1b694"}},{"code_sha256_prefix":"2e0587cc12b477e2","entry":"Match_head","repo":"txh-mercury/vast","repo_kind":"official","path":"model/vast.py","file_url":"https://github.com/txh-mercury/vast/blob/HEAD/model/vast.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e0587cc12b477e2"}},{"code_sha256_prefix":"3e58c21b8cf01cc4","entry":"TokenMasker","repo":"txh-mercury/vast","repo_kind":"official","path":"model/vast.py","file_url":"https://github.com/txh-mercury/vast/blob/HEAD/model/vast.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3e58c21b8cf01cc4"}},{"code_sha256_prefix":"98f385d847636a3e","entry":"basic_clean","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/clip_tokenizer.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/clip_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"TXH-mercury/VAST","repo_kind":"official","path":"model/general_module.py","file_url":"https://github.com/TXH-mercury/VAST/blob/HEAD/model/general_module.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"55120f2026b56aa2","entry":"drop_path","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/videoswin.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/videoswin.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"code_sha256_prefix":"fdc64f4c72036ae4","entry":"gelu","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/transformer.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/transformer.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"code_sha256_prefix":"40e9fee2e0b7e278","entry":"gelu","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/bert.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/bert.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/clip_tokenizer.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/clip_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"7810fed39bf5c241","entry":"trunc_normal_","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/videoswin.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/videoswin.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7810fed39bf5c241"}},{"code_sha256_prefix":"af64ec220e8bcdbc","entry":"url_to_filename","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/file_utils.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/file_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"af64ec220e8bcdbc"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/clip_tokenizer.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/clip_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"b6fa06654838e4da","entry":"MMGeneralModule","repo":"txh-mercury/vast","repo_kind":"official","path":"model/vast.py","file_url":"https://github.com/txh-mercury/vast/blob/HEAD/model/vast.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b6fa06654838e4da"}},{"code_sha256_prefix":"c22a88dfed0bd02e","entry":"VAST","repo":"txh-mercury/vast","repo_kind":"official","path":"model/vast.py","file_url":"https://github.com/txh-mercury/vast/blob/HEAD/model/vast.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c22a88dfed0bd02e"}},{"code_sha256_prefix":"eee800bfe0a47a9f","entry":"all_gather_list","repo":"TXH-mercury/VAST","repo_kind":"official","path":"utils/distributed.py","file_url":"https://github.com/TXH-mercury/VAST/blob/HEAD/utils/distributed.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eee800bfe0a47a9f"}},{"code_sha256_prefix":"0ec9fc2025c16f65","entry":"all_gather_with_grad","repo":"txh-mercury/vast","repo_kind":"official","path":"model/vast.py","file_url":"https://github.com/txh-mercury/vast/blob/HEAD/model/vast.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0ec9fc2025c16f65"}},{"code_sha256_prefix":"cc4ffe92873b4ee6","entry":"build_optimizer","repo":"TXH-mercury/VAST","repo_kind":"official","path":"utils/build_optimizer.py","file_url":"https://github.com/TXH-mercury/VAST/blob/HEAD/utils/build_optimizer.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cc4ffe92873b4ee6"}},{"code_sha256_prefix":"349d780dd4a89a37","entry":"cached_path","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/file_utils.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/file_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"349d780dd4a89a37"}},{"code_sha256_prefix":"67dae5beb14eebd7","entry":"clean","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"inference.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"67dae5beb14eebd7"}},{"code_sha256_prefix":"98110ed59394ae02","entry":"clones","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/transformer.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/transformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98110ed59394ae02"}},{"code_sha256_prefix":"0122d74913461cf9","entry":"compute_max_audio_sample_num_for_position_embeddings","repo":"TXH-mercury/VAST","repo_kind":"official","path":"utils/args.py","file_url":"https://github.com/TXH-mercury/VAST/blob/HEAD/utils/args.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0122d74913461cf9"}},{"code_sha256_prefix":"30fd4a1a3eedb19c","entry":"compute_max_vision_sample_num_for_position_embeddings","repo":"TXH-mercury/VAST","repo_kind":"official","path":"utils/args.py","file_url":"https://github.com/TXH-mercury/VAST/blob/HEAD/utils/args.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"30fd4a1a3eedb19c"}},{"code_sha256_prefix":"73cecca9f3575f09","entry":"concat_all_gather","repo":"TXH-mercury/VAST","repo_kind":"official","path":"utils/distributed.py","file_url":"https://github.com/TXH-mercury/VAST/blob/HEAD/utils/distributed.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73cecca9f3575f09"}},{"code_sha256_prefix":"6c465efd98518ed2","entry":"cook_refs","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"scorer/bleu_scorer.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/scorer/bleu_scorer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c465efd98518ed2"}},{"code_sha256_prefix":"fb961e80ca3db085","entry":"cook_test","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"scorer/bleu_scorer.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/scorer/bleu_scorer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb961e80ca3db085"}},{"code_sha256_prefix":"77a45c1e515dbe2e","entry":"execCmd","repo":"TXH-mercury/VAST","repo_kind":"official","path":"utils/offline_process_data.py","file_url":"https://github.com/TXH-mercury/VAST/blob/HEAD/utils/offline_process_data.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"77a45c1e515dbe2e"}},{"code_sha256_prefix":"db0ac56aaf6e35e6","entry":"filename_to_url","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/file_utils.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/file_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"db0ac56aaf6e35e6"}},{"code_sha256_prefix":"36075dd106d2bbbe","entry":"get_best_name","repo":"TXH-mercury/VAST","repo_kind":"official","path":"utils/pipeline.py","file_url":"https://github.com/TXH-mercury/VAST/blob/HEAD/utils/pipeline.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"36075dd106d2bbbe"}},{"code_sha256_prefix":"b65e5286fa81fca8","entry":"get_padded_tokens","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"inference.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b65e5286fa81fca8"}},{"code_sha256_prefix":"7d297bdebd282cba","entry":"load_from_pretrained_dir","repo":"TXH-mercury/VAST","repo_kind":"official","path":"utils/build_model.py","file_url":"https://github.com/TXH-mercury/VAST/blob/HEAD/utils/build_model.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d297bdebd282cba"}},{"code_sha256_prefix":"647f671c01bde501","entry":"load_from_resume","repo":"TXH-mercury/VAST","repo_kind":"official","path":"utils/build_model.py","file_url":"https://github.com/TXH-mercury/VAST/blob/HEAD/utils/build_model.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"647f671c01bde501"}},{"code_sha256_prefix":"fb95c4b13cdf89a2","entry":"load_vocab","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/bert_tokenizer.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/bert_tokenizer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb95c4b13cdf89a2"}},{"code_sha256_prefix":"15b65a6a6e8fd954","entry":"parse_with_config","repo":"TXH-mercury/VAST","repo_kind":"official","path":"utils/args.py","file_url":"https://github.com/TXH-mercury/VAST/blob/HEAD/utils/args.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"15b65a6a6e8fd954"}},{"code_sha256_prefix":"aad08f61905b40a5","entry":"precook","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"scorer/bleu_scorer.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/scorer/bleu_scorer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aad08f61905b40a5"}},{"code_sha256_prefix":"d92ebd9f3d882489","entry":"split","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"inference.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d92ebd9f3d882489"}},{"code_sha256_prefix":"8b5247b663a8f1b5","entry":"trans","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/modeling.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8b5247b663a8f1b5"}},{"code_sha256_prefix":"3df7530a6ef7c69d","entry":"valid","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/modeling.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3df7530a6ef7c69d"}},{"code_sha256_prefix":"da7295883cd7da14","entry":"whitespace_tokenize","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/bert_tokenizer.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/bert_tokenizer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da7295883cd7da14"}},{"code_sha256_prefix":"ed4b0e420c5e9bde","entry":"window_partition","repo":"TXH-mercury/VALOR","repo_kind":"listed","path":"model/videoswin.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/videoswin.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed4b0e420c5e9bde"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}