{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HD53LQPHJMHVWJJBUA2TOOUJUP","short_pith_number":"pith:HD53LQPH","schema_version":"1.0","canonical_sha256":"38fbb5c1e74b0f5b2521a035373a89a3f29b8ac5f3fe0792f7fe3bf90dd3ff4f","source":{"kind":"arxiv","id":"2507.01949","version":1},"attestation_state":"computed","paper":{"title":"Kwai Keye-VL Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Yang, Bin Wen, Changyi Liu, Chenglong Chu, Chengru Song, Chongling Rao, Chuan Yi, Da Li, Dehua Ma, Di Xu, Dunju Zang, Fan Yang, Guorui Zhou, Haixuan Gao, Hang Li, Haojie Ding, Hao Peng, Jiaming Huang, Jiangxia Cao, Jiankang Chen, Jiawei Guo, Jing Wang, Jingyun Hua, Jin Ouyang, Kaibing Chen, Kaiyu Jiang, Kaiyu Tang, Kun Gai, Kwai Keye Team, Lejian Ren, Muhao Wei, Qianqian Wang, Qigen Hu, Shengnan Zhang, Shiyao Wang, Siyang Mao, Sui Huang, Tao Yu, Tianke Zhang, Tingting Gao, Wei Chen, Wei Yuan, Xiangyu Wu, Xiao Hu, Xinchen Luo, Xingyu Lu, Yang Zhou, Yan Li, Yi-Fan Zhang, Yiming Liang, Yiping Yang, Yuhang Hu, Yulong Chen, Zeyi Lu, Zhenhua Wu, Zhenyu Li, Zhixin Ling, Zhuoran Yang, Ziming Li, Zixing Zhang","submitted_at":"2025-07-02T17:57:28Z","abstract_excerpt":"While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities on static images, they often fall short in comprehending dynamic, information-dense short-form videos, a dominant medium in today's digital landscape. To bridge this gap, we introduce \\textbf{Kwai Keye-VL}, an 8-billion-parameter multimodal foundation model engineered for leading-edge performance in short-video understanding while maintaining robust general-purpose vision-language abilities. The development of Keye-VL rests on two core pillars: a massive, high-quality dataset exceeding 600 billion tokens with a "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.01949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T17:57:28Z","cross_cats_sorted":[],"title_canon_sha256":"ed1a32c9a90acca9abeae9a53923ae2a629c64998172d40a3dc54404c2b3f434","abstract_canon_sha256":"fdbeb94b889744aa07dcb7f791218d15bf1d175d8aaccd77f31f3a30f47fac8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:58.938301Z","signature_b64":"WjA6BGFcSuITwAI9I5qUDkUm32TSbBGEKVL9dJKP6Af+FCqkgse26ZgJoDV2anlT/a3onWt14xTOGyvhV7kyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38fbb5c1e74b0f5b2521a035373a89a3f29b8ac5f3fe0792f7fe3bf90dd3ff4f","last_reissued_at":"2026-07-05T11:30:58.937739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:58.937739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kwai Keye-VL Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Yang, Bin Wen, Changyi Liu, Chenglong Chu, Chengru Song, Chongling Rao, Chuan Yi, Da Li, Dehua Ma, Di Xu, Dunju Zang, Fan Yang, Guorui Zhou, Haixuan Gao, Hang Li, Haojie Ding, Hao Peng, Jiaming Huang, Jiangxia Cao, Jiankang Chen, Jiawei Guo, Jing Wang, Jingyun Hua, Jin Ouyang, Kaibing Chen, Kaiyu Jiang, Kaiyu Tang, Kun Gai, Kwai Keye Team, Lejian Ren, Muhao Wei, Qianqian Wang, Qigen Hu, Shengnan Zhang, Shiyao Wang, Siyang Mao, Sui Huang, Tao Yu, Tianke Zhang, Tingting Gao, Wei Chen, Wei Yuan, Xiangyu Wu, Xiao Hu, Xinchen Luo, Xingyu Lu, Yang Zhou, Yan Li, Yi-Fan Zhang, Yiming Liang, Yiping Yang, Yuhang Hu, Yulong Chen, Zeyi Lu, Zhenhua Wu, Zhenyu Li, Zhixin Ling, Zhuoran Yang, Ziming Li, Zixing Zhang","submitted_at":"2025-07-02T17:57:28Z","abstract_excerpt":"While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities on static images, they often fall short in comprehending dynamic, information-dense short-form videos, a dominant medium in today's digital landscape. To bridge this gap, we introduce \\textbf{Kwai Keye-VL}, an 8-billion-parameter multimodal foundation model engineered for leading-edge performance in short-video understanding while maintaining robust general-purpose vision-language abilities. The development of Keye-VL rests on two core pillars: a massive, high-quality dataset exceeding 600 billion tokens with a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01949","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.01949/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.01949","created_at":"2026-07-05T11:30:58.937816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01949v1","created_at":"2026-07-05T11:30:58.937816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01949","created_at":"2026-07-05T11:30:58.937816+00:00"},{"alias_kind":"pith_short_12","alias_value":"HD53LQPHJMHV","created_at":"2026-07-05T11:30:58.937816+00:00"},{"alias_kind":"pith_short_16","alias_value":"HD53LQPHJMHVWJJB","created_at":"2026-07-05T11:30:58.937816+00:00"},{"alias_kind":"pith_short_8","alias_value":"HD53LQPH","created_at":"2026-07-05T11:30:58.937816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06420","citing_title":"HoloCount: A Holistic Visual Counting Benchmark for MLLMs","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10651","citing_title":"Kwai Keye-VL-2.0 Technical Report","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24562","citing_title":"PEDESTRIANQA: A Benchmark for Vision-Language Models on Pedestrian Intention and Trajectory Prediction","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22104","citing_title":"OPERA: An Agent for Image Restoration with End-to-End Joint Planning-Execution Optimization","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22678","citing_title":"Swift Sampling: Selecting Temporal Surprises via Taylor Series","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2508.09521","citing_title":"PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22378","citing_title":"Zero-Effort Image-to-Music Generation: An Interpretable RAG-based VLM Approach","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2603.24326","citing_title":"Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20806","citing_title":"OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01882","citing_title":"Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06777","citing_title":"Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2508.18265","citing_title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","ref_index":127,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HD53LQPHJMHVWJJBUA2TOOUJUP","json":"https://pith.science/pith/HD53LQPHJMHVWJJBUA2TOOUJUP.json","graph_json":"https://pith.science/api/pith-number/HD53LQPHJMHVWJJBUA2TOOUJUP/graph.json","events_json":"https://pith.science/api/pith-number/HD53LQPHJMHVWJJBUA2TOOUJUP/events.json","paper":"https://pith.science/paper/HD53LQPH"},"agent_actions":{"view_html":"https://pith.science/pith/HD53LQPHJMHVWJJBUA2TOOUJUP","download_json":"https://pith.science/pith/HD53LQPHJMHVWJJBUA2TOOUJUP.json","view_paper":"https://pith.science/paper/HD53LQPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01949&json=true","fetch_graph":"https://pith.science/api/pith-number/HD53LQPHJMHVWJJBUA2TOOUJUP/graph.json","fetch_events":"https://pith.science/api/pith-number/HD53LQPHJMHVWJJBUA2TOOUJUP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HD53LQPHJMHVWJJBUA2TOOUJUP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HD53LQPHJMHVWJJBUA2TOOUJUP/action/storage_attestation","attest_author":"https://pith.science/pith/HD53LQPHJMHVWJJBUA2TOOUJUP/action/author_attestation","sign_citation":"https://pith.science/pith/HD53LQPHJMHVWJJBUA2TOOUJUP/action/citation_signature","submit_replication":"https://pith.science/pith/HD53LQPHJMHVWJJBUA2TOOUJUP/action/replication_record"}},"created_at":"2026-07-05T11:30:58.937816+00:00","updated_at":"2026-07-05T11:30:58.937816+00:00"}