{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PGIX3K5A3UNML3I27TSJN6AYEN","short_pith_number":"pith:PGIX3K5A","schema_version":"1.0","canonical_sha256":"79917daba0dd1ac5ed1afce496f81823759426d70fae4338917caca219a88b3c","source":{"kind":"arxiv","id":"2507.05240","version":1},"attestation_state":"computed","paper":{"title":"StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chenming Zhu, Chenyang Wan, Hanqing Wang, Jiangmiao Pang, Meng Wei, Tai Wang, Wenzhe Cai, Xiaohan Mao, Xihui Liu, Xiqian Yu, Yilun Chen, Yuqiang Yang","submitted_at":"2025-07-07T17:49:41Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low latency grounded in language instructions. While Video-based Large Language Models (Video-LLMs) have driven recent progress, current VLN methods based on Video-LLM often face trade-offs among fine-grained visual understanding, long-term context modeling and computational efficiency. We introduce StreamVLN, a streaming VLN framework that employs a hybrid slow-fast context modeling strategy to support multi-modal reasoning over interleaved vision, languag"},"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":"2507.05240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-07-07T17:49:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f69dde350605d567fc41df7d4b7f7a3bb1e7916a1f4d1ba1578e29c0918b01f0","abstract_canon_sha256":"3ef30cd3494e7734d2c2bceec421c0e82b86bcc4ecf08e1111e57a15bc012fb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:11.055224Z","signature_b64":"JiCmnegp4rr+YZBp20NgCJGfLxBbv0KHC4R8ff3D+eRcbJX2EhePssJdAWHSciVREiQpkkELHCDIsz3LDw1xDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79917daba0dd1ac5ed1afce496f81823759426d70fae4338917caca219a88b3c","last_reissued_at":"2026-07-05T11:33:11.054777Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:11.054777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chenming Zhu, Chenyang Wan, Hanqing Wang, Jiangmiao Pang, Meng Wei, Tai Wang, Wenzhe Cai, Xiaohan Mao, Xihui Liu, Xiqian Yu, Yilun Chen, Yuqiang Yang","submitted_at":"2025-07-07T17:49:41Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low latency grounded in language instructions. While Video-based Large Language Models (Video-LLMs) have driven recent progress, current VLN methods based on Video-LLM often face trade-offs among fine-grained visual understanding, long-term context modeling and computational efficiency. We introduce StreamVLN, a streaming VLN framework that employs a hybrid slow-fast context modeling strategy to support multi-modal reasoning over interleaved vision, languag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05240","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/2507.05240/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":"2507.05240","created_at":"2026-07-05T11:33:11.054830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05240v1","created_at":"2026-07-05T11:33:11.054830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05240","created_at":"2026-07-05T11:33:11.054830+00:00"},{"alias_kind":"pith_short_12","alias_value":"PGIX3K5A3UNM","created_at":"2026-07-05T11:33:11.054830+00:00"},{"alias_kind":"pith_short_16","alias_value":"PGIX3K5A3UNML3I2","created_at":"2026-07-05T11:33:11.054830+00:00"},{"alias_kind":"pith_short_8","alias_value":"PGIX3K5A","created_at":"2026-07-05T11:33:11.054830+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":35,"internal_anchor_count":35,"sample":[{"citing_arxiv_id":"2607.05765","citing_title":"Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator","ref_index":92,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20458","citing_title":"Slow Brain, Fast Planner: Latency-Resilient VLM-Augmented Urban Navigation","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01754","citing_title":"Path-level Hindsight Instructions for Semantic Exploration in Vision-Language Navigation","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2607.02417","citing_title":"LIME: Learning Intent-aware Camera Motion from Egocentric Video","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07244","citing_title":"Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigation","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2606.01621","citing_title":"Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2606.01241","citing_title":"OneVLA: A Unified Framework for Embodied Tasks","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2605.31121","citing_title":"TARIC: Memory-Augmented Traversability-Aware Outdoor VLN under Interrupted Semantic Cues","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17249","citing_title":"SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30367","citing_title":"FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27807","citing_title":"SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.27582","citing_title":"Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.28237","citing_title":"POINav: Benchmarking and Enhancing Final-Meters Arrival in Real-World Vision-Language Navigation","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22036","citing_title":"GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22816","citing_title":"AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2603.05377","citing_title":"OpenFrontier: General Navigation with Visual-Language Grounded Frontiers","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2603.16947","citing_title":"LightZeroNav: Zero-Shot Vision Language Navigation in Continuous Environments Based on Lightweight VLMs","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17249","citing_title":"SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13169","citing_title":"PanoWorld: Towards Spatial Supersensing in 360$^\\circ$ Panorama World","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2511.17097","citing_title":"Progress-Think: Semantic Progress Reasoning for Vision-Language Navigation","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2512.21714","citing_title":"AstraNav-World: World Model for Foresight Control and Consistency","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2603.07080","citing_title":"VLN-Cache: Enabling Token Caching for VLN Models with Visual/Semantic Dynamics Awareness","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12624","citing_title":"MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12624","citing_title":"MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13169","citing_title":"PanoWorld: Towards Spatial Supersensing in 360$^\\circ$ Panorama World","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PGIX3K5A3UNML3I27TSJN6AYEN","json":"https://pith.science/pith/PGIX3K5A3UNML3I27TSJN6AYEN.json","graph_json":"https://pith.science/api/pith-number/PGIX3K5A3UNML3I27TSJN6AYEN/graph.json","events_json":"https://pith.science/api/pith-number/PGIX3K5A3UNML3I27TSJN6AYEN/events.json","paper":"https://pith.science/paper/PGIX3K5A"},"agent_actions":{"view_html":"https://pith.science/pith/PGIX3K5A3UNML3I27TSJN6AYEN","download_json":"https://pith.science/pith/PGIX3K5A3UNML3I27TSJN6AYEN.json","view_paper":"https://pith.science/paper/PGIX3K5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05240&json=true","fetch_graph":"https://pith.science/api/pith-number/PGIX3K5A3UNML3I27TSJN6AYEN/graph.json","fetch_events":"https://pith.science/api/pith-number/PGIX3K5A3UNML3I27TSJN6AYEN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PGIX3K5A3UNML3I27TSJN6AYEN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PGIX3K5A3UNML3I27TSJN6AYEN/action/storage_attestation","attest_author":"https://pith.science/pith/PGIX3K5A3UNML3I27TSJN6AYEN/action/author_attestation","sign_citation":"https://pith.science/pith/PGIX3K5A3UNML3I27TSJN6AYEN/action/citation_signature","submit_replication":"https://pith.science/pith/PGIX3K5A3UNML3I27TSJN6AYEN/action/replication_record"}},"created_at":"2026-07-05T11:33:11.054830+00:00","updated_at":"2026-07-05T11:33:11.054830+00:00"}