{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PPQJJRR6JS2EFMGIQSOLSRDKHW","short_pith_number":"pith:PPQJJRR6","schema_version":"1.0","canonical_sha256":"7be094c63e4cb442b0c8849cb9446a3db7f263eb3cb1311bf4768c02971e3b80","source":{"kind":"arxiv","id":"2503.10631","version":3},"attestation_state":"computed","paper":{"title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"HybridVLA unifies diffusion for continuous actions and autoregression for reasoning inside one vision-language-action model.","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Chengkai Hou, Chenyang Gu, Hao Chen, Jiaming Liu, KC alex Zhou, Mengdi Zhao, Mengzhen Liu, Pengju An, Pheng-Ann Heng, Renrui Zhang, Shanghang Zhang, Sixiang Chen, Xiaoqi Li, Zhuoyang Liu, Ziyu Guo","submitted_at":"2025-03-13T17:59:52Z","abstract_excerpt":"A fundamental objective of manipulation policy design is to endow robots to comprehend human instructions, reason about scene cues, and execute generalized actions in dynamic environments. Recent autoregressive vision-language-action (VLA) methods inherit common-sense reasoning capabilities from vision-language models (VLMs) for next action-token prediction. However, these methods quantize actions into discrete bins, which disrupts the continuity required for precise control. In contrast, existing diffusion-based VLA methods incorporate an additional diffusion head to predict continuous action"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.10631","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:59:52Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"3547a3a9f5d9e60b9a2fdd4375a5e12e48215603b741ba11840c7c6c0f109329","abstract_canon_sha256":"facb64202c82213c7e5ffa87cf5850af1e79e6f349e74b2fb30c6e601c2a1d0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:50.021385Z","signature_b64":"v+kpGRtOFWqpZLw9ZUMbwpSTkI6bq0JPUWP+PLZdy4JRixVTH+JAtqo20FfHF5ZOamw+gw1jWTqaOSzsf7VXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7be094c63e4cb442b0c8849cb9446a3db7f263eb3cb1311bf4768c02971e3b80","last_reissued_at":"2026-05-17T23:38:50.020884Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:50.020884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"HybridVLA unifies diffusion for continuous actions and autoregression for reasoning inside one vision-language-action model.","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Chengkai Hou, Chenyang Gu, Hao Chen, Jiaming Liu, KC alex Zhou, Mengdi Zhao, Mengzhen Liu, Pengju An, Pheng-Ann Heng, Renrui Zhang, Shanghang Zhang, Sixiang Chen, Xiaoqi Li, Zhuoyang Liu, Ziyu Guo","submitted_at":"2025-03-13T17:59:52Z","abstract_excerpt":"A fundamental objective of manipulation policy design is to endow robots to comprehend human instructions, reason about scene cues, and execute generalized actions in dynamic environments. Recent autoregressive vision-language-action (VLA) methods inherit common-sense reasoning capabilities from vision-language models (VLMs) for next action-token prediction. However, these methods quantize actions into discrete bins, which disrupts the continuity required for precise control. In contrast, existing diffusion-based VLA methods incorporate an additional diffusion head to predict continuous action"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"HybridVLA outperforms previous state-of-the-art VLA methods by 14% and 19% in mean success rate on simulation and real-world tasks, respectively, while demonstrating stable manipulation in unseen configurations.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The collaborative training recipe successfully prevents interference between diffusion denoising and next-token prediction while allowing the two paradigms to reinforce each other across tasks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"HybridVLA unifies diffusion for continuous actions and autoregression for reasoning inside one vision-language-action model.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f60d62d555cb87ba1712b6516e4b2f2529fa7f4897ada1c2047204adbd6a44dd"},"source":{"id":"2503.10631","kind":"arxiv","version":3},"verdict":{"id":"17f48075-055a-45b6-b90c-25bba68fbb29","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T21:57:10.964919Z","strongest_claim":"HybridVLA outperforms previous state-of-the-art VLA methods by 14% and 19% in mean success rate on simulation and real-world tasks, respectively, while demonstrating stable manipulation in unseen configurations.","one_line_summary":"HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The collaborative training recipe successfully prevents interference between diffusion denoising and next-token prediction while allowing the two paradigms to reinforce each other across tasks.","pith_extraction_headline":"HybridVLA unifies diffusion for continuous actions and autoregression for reasoning inside one vision-language-action model."},"references":{"count":127,"sample":[{"doi":"","year":2023,"title":"PaLM-E: An Embodied Multimodal Language Model","work_id":"5b99811a-1d93-47e2-9d59-f4045a0b74a2","ref_index":1,"cited_arxiv_id":"2303.03378","is_internal_anchor":true},{"doi":"","year":2022,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","ref_index":2,"cited_arxiv_id":"2204.01691","is_internal_anchor":true},{"doi":"","year":2023,"title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","work_id":"5a5edf95-2538-4e2b-8dfa-da39cec89f22","ref_index":3,"cited_arxiv_id":"2307.05973","is_internal_anchor":true},{"doi":"","year":2024,"title":"What Matters in Building Vision-Language-Action Models for Generalist Robots","work_id":"972ba6c7-a312-404e-bd8d-851850b28fc9","ref_index":4,"cited_arxiv_id":"2412.14058","is_internal_anchor":true},{"doi":"","year":2024,"title":"Visual instruction tuning","work_id":"a2628f23-eb28-4e09-a098-bce23f22dee1","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":127,"snapshot_sha256":"6828e62d3c65ce92fbd7fb78972eb241f48387976896d9433f37739a35edf8b1","internal_anchors":42},"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":"2503.10631","created_at":"2026-05-17T23:38:50.020965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10631v3","created_at":"2026-05-17T23:38:50.020965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10631","created_at":"2026-05-17T23:38:50.020965+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPQJJRR6JS2E","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPQJJRR6JS2EFMGI","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPQJJRR6","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":38,"internal_anchor_count":38,"sample":[{"citing_arxiv_id":"2605.23856","citing_title":"Point Tracking Improves World Action Models","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2405.14093","citing_title":"A Survey on Vision-Language-Action Models for Embodied AI","ref_index":126,"is_internal_anchor":true},{"citing_arxiv_id":"2504.16054","citing_title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2602.20200","citing_title":"Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2602.09023","citing_title":"TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2602.19710","citing_title":"Universal Pose Pretraining for Generalizable Vision-Language-Action Policies","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21414","citing_title":"PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07308","citing_title":"AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2505.18780","citing_title":"DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2506.13456","citing_title":"Block-wise Adaptive Caching for Accelerating Diffusion Policy","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2507.12768","citing_title":"AnyPos: Automated Task-Agnostic Actions for Bimanual Manipulation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2511.02776","citing_title":"XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2508.13073","citing_title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2507.01925","citing_title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","ref_index":264,"is_internal_anchor":true},{"citing_arxiv_id":"2512.01773","citing_title":"IGen: Scalable Data Generation for Robot Learning from Open-World Images","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2507.04447","citing_title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","ref_index":86,"is_internal_anchor":true},{"citing_arxiv_id":"2510.10125","citing_title":"Ctrl-World: A Controllable Generative World Model for Robot Manipulation","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2603.00110","citing_title":"Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11459","citing_title":"Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2603.25661","citing_title":"Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2502.05855","citing_title":"DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13316","citing_title":"Test-time Sparsity for Extreme Fast Action Diffusion","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04161","citing_title":"Adaptive Action Chunking at Inference-time for Vision-Language-Action Models","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12167","citing_title":"From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11459","citing_title":"Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PPQJJRR6JS2EFMGIQSOLSRDKHW","json":"https://pith.science/pith/PPQJJRR6JS2EFMGIQSOLSRDKHW.json","graph_json":"https://pith.science/api/pith-number/PPQJJRR6JS2EFMGIQSOLSRDKHW/graph.json","events_json":"https://pith.science/api/pith-number/PPQJJRR6JS2EFMGIQSOLSRDKHW/events.json","paper":"https://pith.science/paper/PPQJJRR6"},"agent_actions":{"view_html":"https://pith.science/pith/PPQJJRR6JS2EFMGIQSOLSRDKHW","download_json":"https://pith.science/pith/PPQJJRR6JS2EFMGIQSOLSRDKHW.json","view_paper":"https://pith.science/paper/PPQJJRR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10631&json=true","fetch_graph":"https://pith.science/api/pith-number/PPQJJRR6JS2EFMGIQSOLSRDKHW/graph.json","fetch_events":"https://pith.science/api/pith-number/PPQJJRR6JS2EFMGIQSOLSRDKHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPQJJRR6JS2EFMGIQSOLSRDKHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPQJJRR6JS2EFMGIQSOLSRDKHW/action/storage_attestation","attest_author":"https://pith.science/pith/PPQJJRR6JS2EFMGIQSOLSRDKHW/action/author_attestation","sign_citation":"https://pith.science/pith/PPQJJRR6JS2EFMGIQSOLSRDKHW/action/citation_signature","submit_replication":"https://pith.science/pith/PPQJJRR6JS2EFMGIQSOLSRDKHW/action/replication_record"}},"created_at":"2026-05-17T23:38:50.020965+00:00","updated_at":"2026-05-17T23:38:50.020965+00:00"}