{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MV47MSE3RRT7TQSRDWJGCQQ3TE","short_pith_number":"pith:MV47MSE3","schema_version":"1.0","canonical_sha256":"6579f6489b8c67f9c2511d9261421b991e1669b312c24b1324f41e57e599beed","source":{"kind":"arxiv","id":"2405.18418","version":3},"attestation_state":"computed","paper":{"title":"Hierarchical World Models as Visual Whole-Body Humanoid Controllers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Hao Su, Jyothir S V, Nicklas Hansen, Vlad Sobal, Xiaolong Wang, Yann LeCun","submitted_at":"2024-05-28T17:57:23Z","abstract_excerpt":"Whole-body control for humanoids is challenging due to the high-dimensional nature of the problem, coupled with the inherent instability of a bipedal morphology. Learning from visual observations further exacerbates this difficulty. In this work, we explore highly data-driven approaches to visual whole-body humanoid control based on reinforcement learning, without any simplifying assumptions, reward design, or skill primitives. Specifically, we propose a hierarchical world model in which a high-level agent generates commands based on visual observations for a low-level agent to execute, both o"},"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":"2405.18418","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T17:57:23Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"5fa2c18c5b34af29ad904668d5e27df671c887ed630c4679b26de8070e937afd","abstract_canon_sha256":"290b4a1186e8d1232ef19737316d099c6f54172cd11eec1709d192f7f368df87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:14.912446Z","signature_b64":"nokerW+Vq/jI+yglAtIdWSU3uJuFSo1WifudcRfupQznKOa2AxJ5SHvL67ay3y6JbOA31i2EudSgAHBC+T5KDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6579f6489b8c67f9c2511d9261421b991e1669b312c24b1324f41e57e599beed","last_reissued_at":"2026-07-05T11:03:14.911926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:14.911926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical World Models as Visual Whole-Body Humanoid Controllers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Hao Su, Jyothir S V, Nicklas Hansen, Vlad Sobal, Xiaolong Wang, Yann LeCun","submitted_at":"2024-05-28T17:57:23Z","abstract_excerpt":"Whole-body control for humanoids is challenging due to the high-dimensional nature of the problem, coupled with the inherent instability of a bipedal morphology. Learning from visual observations further exacerbates this difficulty. In this work, we explore highly data-driven approaches to visual whole-body humanoid control based on reinforcement learning, without any simplifying assumptions, reward design, or skill primitives. Specifically, we propose a hierarchical world model in which a high-level agent generates commands based on visual observations for a low-level agent to execute, both o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18418","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/2405.18418/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":"2405.18418","created_at":"2026-07-05T11:03:14.911991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18418v3","created_at":"2026-07-05T11:03:14.911991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18418","created_at":"2026-07-05T11:03:14.911991+00:00"},{"alias_kind":"pith_short_12","alias_value":"MV47MSE3RRT7","created_at":"2026-07-05T11:03:14.911991+00:00"},{"alias_kind":"pith_short_16","alias_value":"MV47MSE3RRT7TQSR","created_at":"2026-07-05T11:03:14.911991+00:00"},{"alias_kind":"pith_short_8","alias_value":"MV47MSE3","created_at":"2026-07-05T11:03:14.911991+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19242","citing_title":"PhyWorld: Physics-Faithful World Model for Video Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11758","citing_title":"HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11075","citing_title":"RISE: Self-Improving Robot Policy with Compositional World Model","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03208","citing_title":"Hierarchical Planning with Latent World Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23532","citing_title":"Emotion-Conditioned Short-Horizon Human Pose Forecasting with a Lightweight Predictive World Model","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16592","citing_title":"Human Cognition in Machines: A Unified Perspective of World Models","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MV47MSE3RRT7TQSRDWJGCQQ3TE","json":"https://pith.science/pith/MV47MSE3RRT7TQSRDWJGCQQ3TE.json","graph_json":"https://pith.science/api/pith-number/MV47MSE3RRT7TQSRDWJGCQQ3TE/graph.json","events_json":"https://pith.science/api/pith-number/MV47MSE3RRT7TQSRDWJGCQQ3TE/events.json","paper":"https://pith.science/paper/MV47MSE3"},"agent_actions":{"view_html":"https://pith.science/pith/MV47MSE3RRT7TQSRDWJGCQQ3TE","download_json":"https://pith.science/pith/MV47MSE3RRT7TQSRDWJGCQQ3TE.json","view_paper":"https://pith.science/paper/MV47MSE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18418&json=true","fetch_graph":"https://pith.science/api/pith-number/MV47MSE3RRT7TQSRDWJGCQQ3TE/graph.json","fetch_events":"https://pith.science/api/pith-number/MV47MSE3RRT7TQSRDWJGCQQ3TE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MV47MSE3RRT7TQSRDWJGCQQ3TE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MV47MSE3RRT7TQSRDWJGCQQ3TE/action/storage_attestation","attest_author":"https://pith.science/pith/MV47MSE3RRT7TQSRDWJGCQQ3TE/action/author_attestation","sign_citation":"https://pith.science/pith/MV47MSE3RRT7TQSRDWJGCQQ3TE/action/citation_signature","submit_replication":"https://pith.science/pith/MV47MSE3RRT7TQSRDWJGCQQ3TE/action/replication_record"}},"created_at":"2026-07-05T11:03:14.911991+00:00","updated_at":"2026-07-05T11:03:14.911991+00:00"}