{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J77D7TEBZ6VZ2NHUAAMBRWXEZH","short_pith_number":"pith:J77D7TEB","schema_version":"1.0","canonical_sha256":"4ffe3fcc81cfab9d34f4001818dae4c9e426544b086e09e4a523d9ee8161425d","source":{"kind":"arxiv","id":"2512.01031","version":2},"attestation_state":"computed","paper":{"title":"VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"James Hou, Jiaming Tang, Shang Yang, Song Han, Yao Lu, Yilong Zhao, Yufei Sun, Yujun Lin, Zhijian Liu, Zhuoyang Zhang","submitted_at":"2025-11-30T18:59:24Z","abstract_excerpt":"Vision-Language-Action models (VLAs) are becoming increasingly capable across diverse robotic tasks. However, these models are typically deployed under synchronous inference, where the robot waits for model inference to complete before acting, and cannot perceive or respond to environmental changes during action execution. This not only introduces noticeable action stalls, but also significantly increases reaction latency, fundamentally limiting the applicability of VLAs to dynamic, real-time tasks. Asynchronous inference offers a promising solution to achieve continuous and low-latency contro"},"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":"2512.01031","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-11-30T18:59:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"19ed6cc02e77cec1b4b022ed26dcb7c1607f139837fc2f368474a705598421d8","abstract_canon_sha256":"7b977dbc7c20a3b9ab3c37513b47e1cce4c4812ca1af7b221c673588dbf9ab8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:25.920736Z","signature_b64":"ANUOZZO5PeYU695qoxZHbIO7LUXv+gAGQaWi7lZq6FwCAWVypFMsQSABWc/5WM5PNsq2GQwj8+f0AxvY+JLCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ffe3fcc81cfab9d34f4001818dae4c9e426544b086e09e4a523d9ee8161425d","last_reissued_at":"2026-07-28T01:22:25.919806Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:25.919806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"James Hou, Jiaming Tang, Shang Yang, Song Han, Yao Lu, Yilong Zhao, Yufei Sun, Yujun Lin, Zhijian Liu, Zhuoyang Zhang","submitted_at":"2025-11-30T18:59:24Z","abstract_excerpt":"Vision-Language-Action models (VLAs) are becoming increasingly capable across diverse robotic tasks. However, these models are typically deployed under synchronous inference, where the robot waits for model inference to complete before acting, and cannot perceive or respond to environmental changes during action execution. This not only introduces noticeable action stalls, but also significantly increases reaction latency, fundamentally limiting the applicability of VLAs to dynamic, real-time tasks. Asynchronous inference offers a promising solution to achieve continuous and low-latency contro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.01031","kind":"arxiv","version":2},"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/2512.01031/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":"2512.01031","created_at":"2026-07-28T01:22:25.920228+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.01031v2","created_at":"2026-07-28T01:22:25.920228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.01031","created_at":"2026-07-28T01:22:25.920228+00:00"},{"alias_kind":"pith_short_12","alias_value":"J77D7TEBZ6VZ","created_at":"2026-07-28T01:22:25.920228+00:00"},{"alias_kind":"pith_short_16","alias_value":"J77D7TEBZ6VZ2NHU","created_at":"2026-07-28T01:22:25.920228+00:00"},{"alias_kind":"pith_short_8","alias_value":"J77D7TEB","created_at":"2026-07-28T01:22:25.920228+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":25,"sample":[{"citing_arxiv_id":"2606.25985","citing_title":"Action ControlNet: A Lightweight Delay-Aware Adapter for Smooth Asynchronous Control in Vision-Language-Action Models","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20458","citing_title":"Slow Brain, Fast Planner: Latency-Resilient VLM-Augmented Urban Navigation","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19774","citing_title":"Start Right, Arrive Right: Asynchronous Execution via Initial Noise Selection","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18589","citing_title":"DREAM-Chunk: Reactive Action Chunking with Latent World Model","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17982","citing_title":"LAGO Policy: Latency-Aware Asynchronous Diffusion Policies with Goal-Directed Collision-Free Planning for Smooth Manipulation","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2606.13355","citing_title":"Real-Time Execution with Autoregressive Policies","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12105","citing_title":"DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12475","citing_title":"Learning to Assist: Collaborative VLAs for Implicit Human-Robot Collaboration","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09615","citing_title":"DexPIE: Stable Dexterous Policy Improvement from Real-World Experience","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01088","citing_title":"ROSA: A Robotics Foundation Model Serving System for Robot Factories","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02486","citing_title":"Intercepting the Future: Latent-Space Predictive World Model for Dynamic VLA Manipulation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.31460","citing_title":"On-Device Robotic Planning: Eliminating Inference Redundancy for Efficient Decision-Making","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2606.28529","citing_title":"The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2606.31497","citing_title":"Communication-Aware Robot Execution for Cloud Inference under Spatially Heterogeneous Connectivity","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.28529","citing_title":"The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25050","citing_title":"DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14598","citing_title":"DSSP: Diffusion State Space Policy with Full-History Encoding","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2603.19199","citing_title":"FASTER: Rethinking Real-Time Flow VLAs","ref_index":80,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19294","citing_title":"DEFLECT: Delay-Robust Execution via Flow-matching Likelihood-Estimated Counterfactual Tuning for VLA Policies","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2603.19199","citing_title":"FASTER: Rethinking Real-Time Flow VLAs","ref_index":80,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11817","citing_title":"See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2601.21998","citing_title":"Causal World Modeling for Robot Control","ref_index":70,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08168","citing_title":"Understanding Asynchronous Inference Methods for Vision-Language-Action Models","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25050","citing_title":"DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24086","citing_title":"AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J77D7TEBZ6VZ2NHUAAMBRWXEZH","json":"https://pith.science/pith/J77D7TEBZ6VZ2NHUAAMBRWXEZH.json","graph_json":"https://pith.science/api/pith-number/J77D7TEBZ6VZ2NHUAAMBRWXEZH/graph.json","events_json":"https://pith.science/api/pith-number/J77D7TEBZ6VZ2NHUAAMBRWXEZH/events.json","paper":"https://pith.science/paper/J77D7TEB"},"agent_actions":{"view_html":"https://pith.science/pith/J77D7TEBZ6VZ2NHUAAMBRWXEZH","download_json":"https://pith.science/pith/J77D7TEBZ6VZ2NHUAAMBRWXEZH.json","view_paper":"https://pith.science/paper/J77D7TEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.01031&json=true","fetch_graph":"https://pith.science/api/pith-number/J77D7TEBZ6VZ2NHUAAMBRWXEZH/graph.json","fetch_events":"https://pith.science/api/pith-number/J77D7TEBZ6VZ2NHUAAMBRWXEZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J77D7TEBZ6VZ2NHUAAMBRWXEZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J77D7TEBZ6VZ2NHUAAMBRWXEZH/action/storage_attestation","attest_author":"https://pith.science/pith/J77D7TEBZ6VZ2NHUAAMBRWXEZH/action/author_attestation","sign_citation":"https://pith.science/pith/J77D7TEBZ6VZ2NHUAAMBRWXEZH/action/citation_signature","submit_replication":"https://pith.science/pith/J77D7TEBZ6VZ2NHUAAMBRWXEZH/action/replication_record"}},"created_at":"2026-07-28T01:22:25.920228+00:00","updated_at":"2026-07-28T01:22:25.920228+00:00"}