{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WDCQVJMPTOMGY6UJLKBEUL5DX6","short_pith_number":"pith:WDCQVJMP","schema_version":"1.0","canonical_sha256":"b0c50aa58f9b986c7a895a824a2fa3bf8d4aceb931b22d1f1f24560090d1d1e2","source":{"kind":"arxiv","id":"2412.13196","version":2},"attestation_state":"computed","paper":{"title":"ExBody2: Advanced Expressive Humanoid Whole-Body Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Fangchen Liu, Ge Yang, Jialong Li, Mazeyu Ji, Xiaolong Wang, Xuanbin Peng, Xuxin Cheng","submitted_at":"2024-12-17T18:59:51Z","abstract_excerpt":"This paper tackles the challenge of enabling real-world humanoid robots to perform expressive and dynamic whole-body motions while maintaining overall stability and robustness. We propose Advanced Expressive Whole-Body Control (Exbody2), a method for producing whole-body tracking controllers that are trained on both human motion capture and simulated data and then transferred to the real world. We introduce a technique for decoupling the velocity tracking of the entire body from tracking body landmarks. We use a teacher policy to produce intermediate data that better conforms to the robot's ki"},"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":"2412.13196","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-17T18:59:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fbdff3eb7d9dff2fc1676d46b01bc16f5de5aefd5c685781aed126ca4ef7075b","abstract_canon_sha256":"0d638c62ad4760c467cf056d7966ac6d0d434e86c03de588cd704b0e19b4cd3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:31.123932Z","signature_b64":"TKoJg9N+9ZJ0KyWJ6iuTEKDQaaqL/5IFrQHx9avqGFlgPK1oNGsgvNbtVssTLrCA6uZJ6hffEWkEYN0XD7u8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0c50aa58f9b986c7a895a824a2fa3bf8d4aceb931b22d1f1f24560090d1d1e2","last_reissued_at":"2026-07-05T10:29:31.122964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:31.122964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ExBody2: Advanced Expressive Humanoid Whole-Body Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Fangchen Liu, Ge Yang, Jialong Li, Mazeyu Ji, Xiaolong Wang, Xuanbin Peng, Xuxin Cheng","submitted_at":"2024-12-17T18:59:51Z","abstract_excerpt":"This paper tackles the challenge of enabling real-world humanoid robots to perform expressive and dynamic whole-body motions while maintaining overall stability and robustness. We propose Advanced Expressive Whole-Body Control (Exbody2), a method for producing whole-body tracking controllers that are trained on both human motion capture and simulated data and then transferred to the real world. We introduce a technique for decoupling the velocity tracking of the entire body from tracking body landmarks. We use a teacher policy to produce intermediate data that better conforms to the robot's ki"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13196","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/2412.13196/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":"2412.13196","created_at":"2026-07-05T10:29:31.123093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13196v2","created_at":"2026-07-05T10:29:31.123093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13196","created_at":"2026-07-05T10:29:31.123093+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDCQVJMPTOMG","created_at":"2026-07-05T10:29:31.123093+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDCQVJMPTOMGY6UJ","created_at":"2026-07-05T10:29:31.123093+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDCQVJMP","created_at":"2026-07-05T10:29:31.123093+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":30,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2607.07370","citing_title":"Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2607.08742","citing_title":"ContactMimic: Humanoid Object Interaction via Contact Control","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2607.07370","citing_title":"Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26741","citing_title":"PressMimic: Pressure-Guided Motion Capture and Control for Humanoid Robot Imitation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23680","citing_title":"CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12814","citing_title":"Stubborn: A Streamlined and Unified Reinforcement Learning Framework for Robust Motion Tracking and Fall Recovery for Humanoids","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09215","citing_title":"MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06953","citing_title":"LIMMT: Less is More for Motion Tracking","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06493","citing_title":"HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04829","citing_title":"M3imic: Learning a Versatile Whole-Body Controller for Multimodal Motion Mimicking","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03985","citing_title":"Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03536","citing_title":"Bionic Human-Motion Style Transfer for Physically Executable Whole-Body Control of Humanoid Robots","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28237","citing_title":"Unleashing Infinite Motion: Scaling Expressive Quadrupedal Motion via Generative Video Priors","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24592","citing_title":"MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27676","citing_title":"CWI: Composite Humanoid Whole-Body Imitation System for Loco-manipulation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22272","citing_title":"Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07765","citing_title":"Toward Seamless Physical Human-Humanoid Interaction: Insights from Control, Intent, and Modeling with a Vision for What Comes Next","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19981","citing_title":"CEER: Compliant End-Effector and Root Control as a Unified Interface for Hierarchical Humanoid Loco-Manipulation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22963","citing_title":"Commanding Humanoid by Free-form Language: A Large Language Action Model with Unified Motion Vocabulary","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2601.14617","citing_title":"UniCon: A Unified System for Efficient Robot Learning Transfers","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09628","citing_title":"TeleGate: Whole-Body Humanoid Teleoperation via Gated Expert Selection with Motion Prior","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2508.08241","citing_title":"BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2603.05493","citing_title":"cuRoboV2: Dynamics-Aware Motion Generation with Depth-Fused Distance Fields for High-DoF Robots","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2603.11346","citing_title":"Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22911","citing_title":"RecoverFormer: End-to-End Contact-Aware Recovery for Humanoid Robots","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WDCQVJMPTOMGY6UJLKBEUL5DX6","json":"https://pith.science/pith/WDCQVJMPTOMGY6UJLKBEUL5DX6.json","graph_json":"https://pith.science/api/pith-number/WDCQVJMPTOMGY6UJLKBEUL5DX6/graph.json","events_json":"https://pith.science/api/pith-number/WDCQVJMPTOMGY6UJLKBEUL5DX6/events.json","paper":"https://pith.science/paper/WDCQVJMP"},"agent_actions":{"view_html":"https://pith.science/pith/WDCQVJMPTOMGY6UJLKBEUL5DX6","download_json":"https://pith.science/pith/WDCQVJMPTOMGY6UJLKBEUL5DX6.json","view_paper":"https://pith.science/paper/WDCQVJMP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13196&json=true","fetch_graph":"https://pith.science/api/pith-number/WDCQVJMPTOMGY6UJLKBEUL5DX6/graph.json","fetch_events":"https://pith.science/api/pith-number/WDCQVJMPTOMGY6UJLKBEUL5DX6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDCQVJMPTOMGY6UJLKBEUL5DX6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDCQVJMPTOMGY6UJLKBEUL5DX6/action/storage_attestation","attest_author":"https://pith.science/pith/WDCQVJMPTOMGY6UJLKBEUL5DX6/action/author_attestation","sign_citation":"https://pith.science/pith/WDCQVJMPTOMGY6UJLKBEUL5DX6/action/citation_signature","submit_replication":"https://pith.science/pith/WDCQVJMPTOMGY6UJLKBEUL5DX6/action/replication_record"}},"created_at":"2026-07-05T10:29:31.123093+00:00","updated_at":"2026-07-05T10:29:31.123093+00:00"}