{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5GRWYWP5OCVIJ7RFWAS62WWLDF","short_pith_number":"pith:5GRWYWP5","schema_version":"1.0","canonical_sha256":"e9a36c59fd70aa84fe25b025ed5acb1961c15e932753beb4d8a7cfd8fc86287c","source":{"kind":"arxiv","id":"2509.01563","version":3},"attestation_state":"computed","paper":{"title":"Kwai Keye-VL 1.5 Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Yang, Bin Wen, Boyang Ding, Changyi Liu, Chenglong Chu, Chengru Song, Chongling Rao, Chuan Yi, Da Li, Di Xu, Dunju Zang, Fan Yang, Guorui Zhou, Guowang Zhang, Haixuan Gao, Hang Li, Han Shen, Haojie Ding, Haonan Fan, Hao Peng, Hao Wang, Hengrui Ju, Jiaming Huang, Jiangxia Cao, Jiankang Chen, Jing Wang, Jingyun Hua, Kaibing Chen, Kaiyu Jiang, Kaiyu Tang, Kun Gai, Lejian Ren, Muhao Wei, Qiang Wang, Qianqian Wang, Qigen Hu, Ruitao Wang, Sen Na, Shengnan Zhang, Shiyao Wang, Siyang Mao, Sui Huang, Tianke Zhang, Tingting Gao, Wei Chen, Wei Yuan, Xiangyu Wu, Xiao Hu, Xinchen Luo, Xingyu Lu, Yan Li, Yi-Fan Zhang, Yiping Yang, Yuhang Hu, Yulong Chen, Zeyi Lu, Zhenhua Wu, Zhixin Ling, Zhuoran Yang, Ziming Li, Zixing Zhang","submitted_at":"2025-09-01T15:46:58Z","abstract_excerpt":"In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Models (MLLMs). However, video understanding remains a challenging area due to the dynamic and information-dense nature of videos. Existing models struggle with the trade-off between spatial resolution and temporal coverage when processing video content. We present Keye-VL-1.5, which addresses fundamental challenges in video comprehension through three key innovations. First, we introduce a novel Slow-Fast video encoding"},"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":"2509.01563","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-01T15:46:58Z","cross_cats_sorted":[],"title_canon_sha256":"55b42b922d1a9e0365305b3c84d8610a445b6caa4865e2f53c71ba2f60f8ec77","abstract_canon_sha256":"a9017d786605baf00d11d4740e53039e81c359d9c7f46d105e4ae40cd42e8b13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:19.739549Z","signature_b64":"GXoLIM3LECDVmLL811kwUHNisHZTnDQE6i4F8VbOEEQWHVaE6YL3c+4Ouv75zBBGWGktAAaRq6fvml2WcJxDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9a36c59fd70aa84fe25b025ed5acb1961c15e932753beb4d8a7cfd8fc86287c","last_reissued_at":"2026-07-05T12:06:19.739027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:19.739027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kwai Keye-VL 1.5 Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Yang, Bin Wen, Boyang Ding, Changyi Liu, Chenglong Chu, Chengru Song, Chongling Rao, Chuan Yi, Da Li, Di Xu, Dunju Zang, Fan Yang, Guorui Zhou, Guowang Zhang, Haixuan Gao, Hang Li, Han Shen, Haojie Ding, Haonan Fan, Hao Peng, Hao Wang, Hengrui Ju, Jiaming Huang, Jiangxia Cao, Jiankang Chen, Jing Wang, Jingyun Hua, Kaibing Chen, Kaiyu Jiang, Kaiyu Tang, Kun Gai, Lejian Ren, Muhao Wei, Qiang Wang, Qianqian Wang, Qigen Hu, Ruitao Wang, Sen Na, Shengnan Zhang, Shiyao Wang, Siyang Mao, Sui Huang, Tianke Zhang, Tingting Gao, Wei Chen, Wei Yuan, Xiangyu Wu, Xiao Hu, Xinchen Luo, Xingyu Lu, Yan Li, Yi-Fan Zhang, Yiping Yang, Yuhang Hu, Yulong Chen, Zeyi Lu, Zhenhua Wu, Zhixin Ling, Zhuoran Yang, Ziming Li, Zixing Zhang","submitted_at":"2025-09-01T15:46:58Z","abstract_excerpt":"In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Models (MLLMs). However, video understanding remains a challenging area due to the dynamic and information-dense nature of videos. Existing models struggle with the trade-off between spatial resolution and temporal coverage when processing video content. We present Keye-VL-1.5, which addresses fundamental challenges in video comprehension through three key innovations. First, we introduce a novel Slow-Fast video encoding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01563","kind":"arxiv","version":3},"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/2509.01563/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":"2509.01563","created_at":"2026-07-05T12:06:19.739082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01563v3","created_at":"2026-07-05T12:06:19.739082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01563","created_at":"2026-07-05T12:06:19.739082+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GRWYWP5OCVI","created_at":"2026-07-05T12:06:19.739082+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GRWYWP5OCVIJ7RF","created_at":"2026-07-05T12:06:19.739082+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GRWYWP5","created_at":"2026-07-05T12:06:19.739082+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24602","citing_title":"ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12195","citing_title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10651","citing_title":"Kwai Keye-VL-2.0 Technical Report","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07433","citing_title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","ref_index":216,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02522","citing_title":"Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30026","citing_title":"MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25706","citing_title":"Towards Open-World Referring Expression Comprehension: A Benchmark with Training-free Multi-task Consistency Checker","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25364","citing_title":"Can MLLMs Reason Beyond Language? VisReason: A Comprehensive Benchmark for Vision-Centric Reasoning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25979","citing_title":"LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27074","citing_title":"IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27365","citing_title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02569","citing_title":"AdaCodec: A Predictive Visual Code for Video MLLMs","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2408.07666","citing_title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","ref_index":267,"is_internal_anchor":false},{"citing_arxiv_id":"2512.21334","citing_title":"Streaming Video Instruction Tuning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2601.10611","citing_title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","ref_index":170,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10187","citing_title":"SciVQR: A Multidisciplinary Multimodal Benchmark for Advanced Scientific Reasoning Evaluation","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10187","citing_title":"SciVQR: A Multidisciplinary Multimodal Benchmark for Advanced Scientific Reasoning Evaluation","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09422","citing_title":"Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00444","citing_title":"Scaling Video Understanding via Compact Latent Multi-Agent Collaboration","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21718","citing_title":"Building a Precise Video Language with Human-AI Oversight","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11627","citing_title":"POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13029","citing_title":"Visual Preference Optimization with Rubric Rewards","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07772","citing_title":"ESOM: Efficiently Understanding Streaming Video Anomalies with Open-world Dynamic Definitions","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05015","citing_title":"Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5GRWYWP5OCVIJ7RFWAS62WWLDF","json":"https://pith.science/pith/5GRWYWP5OCVIJ7RFWAS62WWLDF.json","graph_json":"https://pith.science/api/pith-number/5GRWYWP5OCVIJ7RFWAS62WWLDF/graph.json","events_json":"https://pith.science/api/pith-number/5GRWYWP5OCVIJ7RFWAS62WWLDF/events.json","paper":"https://pith.science/paper/5GRWYWP5"},"agent_actions":{"view_html":"https://pith.science/pith/5GRWYWP5OCVIJ7RFWAS62WWLDF","download_json":"https://pith.science/pith/5GRWYWP5OCVIJ7RFWAS62WWLDF.json","view_paper":"https://pith.science/paper/5GRWYWP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01563&json=true","fetch_graph":"https://pith.science/api/pith-number/5GRWYWP5OCVIJ7RFWAS62WWLDF/graph.json","fetch_events":"https://pith.science/api/pith-number/5GRWYWP5OCVIJ7RFWAS62WWLDF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GRWYWP5OCVIJ7RFWAS62WWLDF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GRWYWP5OCVIJ7RFWAS62WWLDF/action/storage_attestation","attest_author":"https://pith.science/pith/5GRWYWP5OCVIJ7RFWAS62WWLDF/action/author_attestation","sign_citation":"https://pith.science/pith/5GRWYWP5OCVIJ7RFWAS62WWLDF/action/citation_signature","submit_replication":"https://pith.science/pith/5GRWYWP5OCVIJ7RFWAS62WWLDF/action/replication_record"}},"created_at":"2026-07-05T12:06:19.739082+00:00","updated_at":"2026-07-05T12:06:19.739082+00:00"}