{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FR7IAAAWCWMOA2ZCVDRXQOONTY","short_pith_number":"pith:FR7IAAAW","schema_version":"1.0","canonical_sha256":"2c7e8000161598e06b22a8e37839cd9e22c0cb0ca7539f4da567077d0a4ad252","source":{"kind":"arxiv","id":"2410.15959","version":6},"attestation_state":"computed","paper":{"title":"Diffusion Transformer Policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chengyang Zhao, Hengjun Pu, Jifeng Dai, Ronglei Tong, Tianyi Zhang, Yuntao Chen, Yu Qiao, Yuwen Xiong, Zhi Hou","submitted_at":"2024-10-21T12:43:54Z","abstract_excerpt":"Recent large vision-language-action models pretrained on diverse robot datasets have demonstrated the potential for generalizing to new environments with a few in-domain data. However, those approaches usually predict individual discretized or continuous action by a small action head, which limits the ability in handling diverse action spaces. In contrast, we model the continuous action sequence with a large multi-modal diffusion transformer, dubbed as Diffusion Transformer Policy, in which we directly denoise action chunks by a large transformer model rather than a small action head for actio"},"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":"2410.15959","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-21T12:43:54Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c8edb5f64d388443af6b3a1f9e631392007994011691ed092b36cd3757ebe55c","abstract_canon_sha256":"86c9cd50849d55175492345802682756029b1711611a9557c3f45d802760b34f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:35.577087Z","signature_b64":"/1lGYh+uZi9IrMI9tb/07cP2O6U0wYOR4FkzdAqfQTieqvTaK9pZ6Sxn86ai+bI04JRvxO8hc0F3csOtcK7xCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c7e8000161598e06b22a8e37839cd9e22c0cb0ca7539f4da567077d0a4ad252","last_reissued_at":"2026-07-05T10:37:35.576129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:35.576129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Transformer Policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chengyang Zhao, Hengjun Pu, Jifeng Dai, Ronglei Tong, Tianyi Zhang, Yuntao Chen, Yu Qiao, Yuwen Xiong, Zhi Hou","submitted_at":"2024-10-21T12:43:54Z","abstract_excerpt":"Recent large vision-language-action models pretrained on diverse robot datasets have demonstrated the potential for generalizing to new environments with a few in-domain data. However, those approaches usually predict individual discretized or continuous action by a small action head, which limits the ability in handling diverse action spaces. In contrast, we model the continuous action sequence with a large multi-modal diffusion transformer, dubbed as Diffusion Transformer Policy, in which we directly denoise action chunks by a large transformer model rather than a small action head for actio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15959","kind":"arxiv","version":6},"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/2410.15959/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":"2410.15959","created_at":"2026-07-05T10:37:35.576212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.15959v6","created_at":"2026-07-05T10:37:35.576212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15959","created_at":"2026-07-05T10:37:35.576212+00:00"},{"alias_kind":"pith_short_12","alias_value":"FR7IAAAWCWMO","created_at":"2026-07-05T10:37:35.576212+00:00"},{"alias_kind":"pith_short_16","alias_value":"FR7IAAAWCWMOA2ZC","created_at":"2026-07-05T10:37:35.576212+00:00"},{"alias_kind":"pith_short_8","alias_value":"FR7IAAAW","created_at":"2026-07-05T10:37:35.576212+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07076","citing_title":"PriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26800","citing_title":"SSI-Policy: Learning Structured Scene Interfaces for Vision-Language Robotic Manipulation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20209","citing_title":"FlowMaps: Modeling Long-Term Multimodal Object Dynamics with Flow Matching","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10818","citing_title":"IMPACT: Learning Internal-Model Predictive Control for Forceful Robotic Manipulation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10371","citing_title":"Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03392","citing_title":"OpenEAI-Platform: An Open-source Embodied Artificial Intelligence Hardware-Software Unified Platform","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00229","citing_title":"Continuous Reasoning for Vision-Language-Action","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26800","citing_title":"SSI-Policy: Learning Structured Scene Interfaces for Vision-Language Robotic Manipulation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29570","citing_title":"Hierarchical Policy Learning via Spectral Decomposition","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10371","citing_title":"Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17522","citing_title":"RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13456","citing_title":"Block-wise Adaptive Caching for Accelerating Diffusion Policy","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17640","citing_title":"RESample: A Robust Data Augmentation Framework via Exploratory Sampling for Robotic Manipulation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2411.19650","citing_title":"CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2506.21539","citing_title":"WorldVLA: Towards Autoregressive Action World Model","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24622","citing_title":"CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2502.19645","citing_title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14732","citing_title":"World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FR7IAAAWCWMOA2ZCVDRXQOONTY","json":"https://pith.science/pith/FR7IAAAWCWMOA2ZCVDRXQOONTY.json","graph_json":"https://pith.science/api/pith-number/FR7IAAAWCWMOA2ZCVDRXQOONTY/graph.json","events_json":"https://pith.science/api/pith-number/FR7IAAAWCWMOA2ZCVDRXQOONTY/events.json","paper":"https://pith.science/paper/FR7IAAAW"},"agent_actions":{"view_html":"https://pith.science/pith/FR7IAAAWCWMOA2ZCVDRXQOONTY","download_json":"https://pith.science/pith/FR7IAAAWCWMOA2ZCVDRXQOONTY.json","view_paper":"https://pith.science/paper/FR7IAAAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.15959&json=true","fetch_graph":"https://pith.science/api/pith-number/FR7IAAAWCWMOA2ZCVDRXQOONTY/graph.json","fetch_events":"https://pith.science/api/pith-number/FR7IAAAWCWMOA2ZCVDRXQOONTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FR7IAAAWCWMOA2ZCVDRXQOONTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FR7IAAAWCWMOA2ZCVDRXQOONTY/action/storage_attestation","attest_author":"https://pith.science/pith/FR7IAAAWCWMOA2ZCVDRXQOONTY/action/author_attestation","sign_citation":"https://pith.science/pith/FR7IAAAWCWMOA2ZCVDRXQOONTY/action/citation_signature","submit_replication":"https://pith.science/pith/FR7IAAAWCWMOA2ZCVDRXQOONTY/action/replication_record"}},"created_at":"2026-07-05T10:37:35.576212+00:00","updated_at":"2026-07-05T10:37:35.576212+00:00"}