{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AP6LRYXTVCMVHPK3677Z7V5D7E","short_pith_number":"pith:AP6LRYXT","schema_version":"1.0","canonical_sha256":"03fcb8e2f3a89953bd5bf7ff9fd7a3f929fb6735be3fc5bde48d19637fc57428","source":{"kind":"arxiv","id":"2501.13468","version":1},"attestation_state":"computed","paper":{"title":"Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haomiao Xiong, Huchuan Lu, Jiawen Zhu, Jiazuo Yu, Lu Zhang, Yunzhi Zhuge, Zongxin Yang","submitted_at":"2025-01-23T08:33:10Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have enabled the development of Video-LLMs, advancing multimodal learning by bridging video data with language tasks. However, current video understanding models struggle with processing long video sequences, supporting multi-turn dialogues, and adapting to real-world dynamic scenarios. To address these issues, we propose StreamChat, a training-free framework for streaming video reasoning and conversational interaction. $\\StreamChat$ leverages a novel hierarchical memory system to efficiently process and compress video features over extended sequ"},"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":"2501.13468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T08:33:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cbff518f6eb926d4d654f54ae31fe05db15eac5d446141a36250d432d31844bd","abstract_canon_sha256":"31c9e34952c81a465dacee8d9c13c6950253a93de616d2a43aa6cb30c851d787"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:29.069828Z","signature_b64":"eISGd0lqXXEYqg3+lpkwYrkZDgkUlwITKHBBHQUZpGDVK5v0StX60Tb3kPqe5iGtKLsarG4D/J/8fk+Qeo9hCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03fcb8e2f3a89953bd5bf7ff9fd7a3f929fb6735be3fc5bde48d19637fc57428","last_reissued_at":"2026-07-05T10:04:29.069351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:29.069351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haomiao Xiong, Huchuan Lu, Jiawen Zhu, Jiazuo Yu, Lu Zhang, Yunzhi Zhuge, Zongxin Yang","submitted_at":"2025-01-23T08:33:10Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have enabled the development of Video-LLMs, advancing multimodal learning by bridging video data with language tasks. However, current video understanding models struggle with processing long video sequences, supporting multi-turn dialogues, and adapting to real-world dynamic scenarios. To address these issues, we propose StreamChat, a training-free framework for streaming video reasoning and conversational interaction. $\\StreamChat$ leverages a novel hierarchical memory system to efficiently process and compress video features over extended sequ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13468","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/2501.13468/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":"2501.13468","created_at":"2026-07-05T10:04:29.069409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13468v1","created_at":"2026-07-05T10:04:29.069409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13468","created_at":"2026-07-05T10:04:29.069409+00:00"},{"alias_kind":"pith_short_12","alias_value":"AP6LRYXTVCMV","created_at":"2026-07-05T10:04:29.069409+00:00"},{"alias_kind":"pith_short_16","alias_value":"AP6LRYXTVCMVHPK3","created_at":"2026-07-05T10:04:29.069409+00:00"},{"alias_kind":"pith_short_8","alias_value":"AP6LRYXT","created_at":"2026-07-05T10:04:29.069409+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19849","citing_title":"ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17798","citing_title":"LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon Streams","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06991","citing_title":"Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05008","citing_title":"M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25621","citing_title":"StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27074","citing_title":"IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27318","citing_title":"Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31557","citing_title":"EGOSTREAM: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01707","citing_title":"StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2512.21334","citing_title":"Streaming Video Instruction Tuning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2601.14724","citing_title":"HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07575","citing_title":"Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24317","citing_title":"Don't Pause! Every prediction matters in a streaming video","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11411","citing_title":"Online Reasoning Video Object Segmentation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2505.07062","citing_title":"Seed1.5-VL Technical Report","ref_index":154,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07575","citing_title":"Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09000","citing_title":"StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17052","citing_title":"OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AP6LRYXTVCMVHPK3677Z7V5D7E","json":"https://pith.science/pith/AP6LRYXTVCMVHPK3677Z7V5D7E.json","graph_json":"https://pith.science/api/pith-number/AP6LRYXTVCMVHPK3677Z7V5D7E/graph.json","events_json":"https://pith.science/api/pith-number/AP6LRYXTVCMVHPK3677Z7V5D7E/events.json","paper":"https://pith.science/paper/AP6LRYXT"},"agent_actions":{"view_html":"https://pith.science/pith/AP6LRYXTVCMVHPK3677Z7V5D7E","download_json":"https://pith.science/pith/AP6LRYXTVCMVHPK3677Z7V5D7E.json","view_paper":"https://pith.science/paper/AP6LRYXT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13468&json=true","fetch_graph":"https://pith.science/api/pith-number/AP6LRYXTVCMVHPK3677Z7V5D7E/graph.json","fetch_events":"https://pith.science/api/pith-number/AP6LRYXTVCMVHPK3677Z7V5D7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AP6LRYXTVCMVHPK3677Z7V5D7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AP6LRYXTVCMVHPK3677Z7V5D7E/action/storage_attestation","attest_author":"https://pith.science/pith/AP6LRYXTVCMVHPK3677Z7V5D7E/action/author_attestation","sign_citation":"https://pith.science/pith/AP6LRYXTVCMVHPK3677Z7V5D7E/action/citation_signature","submit_replication":"https://pith.science/pith/AP6LRYXTVCMVHPK3677Z7V5D7E/action/replication_record"}},"created_at":"2026-07-05T10:04:29.069409+00:00","updated_at":"2026-07-05T10:04:29.069409+00:00"}