{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SILTR7TUVRKMN5BTJN2NZDV3J3","short_pith_number":"pith:SILTR7TU","schema_version":"1.0","canonical_sha256":"921738fe74ac54c6f4334b74dc8ebb4ec3fb302952fc7537bbef0010e4e8c9eb","source":{"kind":"arxiv","id":"2412.03293","version":3},"attestation_state":"computed","paper":{"title":"Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chaomin Shen, Chengmeng Li, Feifei Feng, Jinming Li, Junjie Wen, Minjie Zhu, Xiaoyu Liu, Yaxin Peng, Yichen Zhu, Zhibin Tang, Zhongyi Zhou","submitted_at":"2024-12-04T13:11:38Z","abstract_excerpt":"In this paper, we present DiffusionVLA, a novel framework that seamlessly combines the autoregression model with the diffusion model for learning visuomotor policy. Central to our approach is a next-token prediction objective, enabling the model to reason effectively over the user's query in the context of current observations. Subsequently, a diffusion model is attached to generate robust action outputs. To enhance policy learning through self-reasoning, we introduce a novel reasoning injection module that integrates reasoning phrases directly into the policy learning process. The whole frame"},"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":"2412.03293","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-04T13:11:38Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"100770d8dc0673fdebfd5c0d09ba56b9211072c197c8a3b03174e748039ccd9c","abstract_canon_sha256":"de021872b8b81fa363b7babfdb2a36f74270dc2df804d506d4fce288f3cbfe68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:40.888065Z","signature_b64":"r8At97LK4dBK0Es1LGBnZb/dL8zxhUPTQn3ontZzvA0+RugLRQLSj7ceWj6L/bbU9LMuxeC/NnwoJTaCyxYhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"921738fe74ac54c6f4334b74dc8ebb4ec3fb302952fc7537bbef0010e4e8c9eb","last_reissued_at":"2026-07-05T11:15:40.887499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:40.887499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chaomin Shen, Chengmeng Li, Feifei Feng, Jinming Li, Junjie Wen, Minjie Zhu, Xiaoyu Liu, Yaxin Peng, Yichen Zhu, Zhibin Tang, Zhongyi Zhou","submitted_at":"2024-12-04T13:11:38Z","abstract_excerpt":"In this paper, we present DiffusionVLA, a novel framework that seamlessly combines the autoregression model with the diffusion model for learning visuomotor policy. Central to our approach is a next-token prediction objective, enabling the model to reason effectively over the user's query in the context of current observations. Subsequently, a diffusion model is attached to generate robust action outputs. To enhance policy learning through self-reasoning, we introduce a novel reasoning injection module that integrates reasoning phrases directly into the policy learning process. The whole frame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03293","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/2412.03293/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":"2412.03293","created_at":"2026-07-05T11:15:40.887569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03293v3","created_at":"2026-07-05T11:15:40.887569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03293","created_at":"2026-07-05T11:15:40.887569+00:00"},{"alias_kind":"pith_short_12","alias_value":"SILTR7TUVRKM","created_at":"2026-07-05T11:15:40.887569+00:00"},{"alias_kind":"pith_short_16","alias_value":"SILTR7TUVRKMN5BT","created_at":"2026-07-05T11:15:40.887569+00:00"},{"alias_kind":"pith_short_8","alias_value":"SILTR7TU","created_at":"2026-07-05T11:15:40.887569+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.07076","citing_title":"PriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06564","citing_title":"Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23685","citing_title":"LaST-HD: Learning Latent Physical Reasoning from Scalable Human Data for Robot Manipulation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22794","citing_title":"UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21088","citing_title":"MV-WAM: Manifold-Aware World Action Model with Value Augmentation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11019","citing_title":"Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06155","citing_title":"AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30686","citing_title":"Position: Vision-Language-Action Models Cannot Be Verified to Perform Physical Reasoning","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09023","citing_title":"TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2505.18780","citing_title":"DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13456","citing_title":"Block-wise Adaptive Caching for Accelerating Diffusion Policy","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14148","citing_title":"AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01925","citing_title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","ref_index":290,"is_internal_anchor":false},{"citing_arxiv_id":"2503.07608","citing_title":"AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20239","citing_title":"TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2503.10631","citing_title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2502.05855","citing_title":"DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13775","citing_title":"RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":269,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28192","citing_title":"LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10942","citing_title":"HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10821","citing_title":"UniSteer: Unified Noise Steering for Efficient Human-Guided VLA Adaptation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2506.21539","citing_title":"WorldVLA: Towards Autoregressive Action World Model","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28192","citing_title":"LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SILTR7TUVRKMN5BTJN2NZDV3J3","json":"https://pith.science/pith/SILTR7TUVRKMN5BTJN2NZDV3J3.json","graph_json":"https://pith.science/api/pith-number/SILTR7TUVRKMN5BTJN2NZDV3J3/graph.json","events_json":"https://pith.science/api/pith-number/SILTR7TUVRKMN5BTJN2NZDV3J3/events.json","paper":"https://pith.science/paper/SILTR7TU"},"agent_actions":{"view_html":"https://pith.science/pith/SILTR7TUVRKMN5BTJN2NZDV3J3","download_json":"https://pith.science/pith/SILTR7TUVRKMN5BTJN2NZDV3J3.json","view_paper":"https://pith.science/paper/SILTR7TU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03293&json=true","fetch_graph":"https://pith.science/api/pith-number/SILTR7TUVRKMN5BTJN2NZDV3J3/graph.json","fetch_events":"https://pith.science/api/pith-number/SILTR7TUVRKMN5BTJN2NZDV3J3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SILTR7TUVRKMN5BTJN2NZDV3J3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SILTR7TUVRKMN5BTJN2NZDV3J3/action/storage_attestation","attest_author":"https://pith.science/pith/SILTR7TUVRKMN5BTJN2NZDV3J3/action/author_attestation","sign_citation":"https://pith.science/pith/SILTR7TUVRKMN5BTJN2NZDV3J3/action/citation_signature","submit_replication":"https://pith.science/pith/SILTR7TUVRKMN5BTJN2NZDV3J3/action/replication_record"}},"created_at":"2026-07-05T11:15:40.887569+00:00","updated_at":"2026-07-05T11:15:40.887569+00:00"}