{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:37P2GXVKUFZGRT2MZSAS73EKLE","short_pith_number":"pith:37P2GXVK","schema_version":"1.0","canonical_sha256":"dfdfa35eaaa17268cf4ccc812fec8a5933fa0f1d856878b88d42237e8d5000b9","source":{"kind":"arxiv","id":"2503.18938","version":4},"attestation_state":"computed","paper":{"title":"AdaWorld: Learning Adaptable World Models with Latent Actions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Chuang Gan, Jun Zhang, Shenyuan Gao, Siyuan Zhou, Yilun Du","submitted_at":"2025-03-24T17:58:15Z","abstract_excerpt":"World models aim to learn action-controlled future prediction and have proven essential for the development of intelligent agents. However, most existing world models rely heavily on substantial action-labeled data and costly training, making it challenging to adapt to novel environments with heterogeneous actions through limited interactions. This limitation can hinder their applicability across broader domains. To overcome this limitation, we propose AdaWorld, an innovative world model learning approach that enables efficient adaptation. The key idea is to incorporate action information duri"},"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":"2503.18938","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-24T17:58:15Z","cross_cats_sorted":["cs.CV","cs.LG","cs.RO"],"title_canon_sha256":"a208522d75b77653f4ff08cb9a7c4d7e3be4e3b0997f40b4387011022ef40cb2","abstract_canon_sha256":"89c3a6fce3fbf17b5076a8be2c4282f4bf2e90095b57cc5412bcc52d1026c967"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:05.955870Z","signature_b64":"m3CtdekUbatKLA8Av9JeYNFjoUPzRxVfcXEAQ+wnqCG6M8pg8hOHoDuXx9GuXEbA8G/JeB23P77aUQbZnEFdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfdfa35eaaa17268cf4ccc812fec8a5933fa0f1d856878b88d42237e8d5000b9","last_reissued_at":"2026-07-05T11:14:05.955364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:05.955364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaWorld: Learning Adaptable World Models with Latent Actions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Chuang Gan, Jun Zhang, Shenyuan Gao, Siyuan Zhou, Yilun Du","submitted_at":"2025-03-24T17:58:15Z","abstract_excerpt":"World models aim to learn action-controlled future prediction and have proven essential for the development of intelligent agents. However, most existing world models rely heavily on substantial action-labeled data and costly training, making it challenging to adapt to novel environments with heterogeneous actions through limited interactions. This limitation can hinder their applicability across broader domains. To overcome this limitation, we propose AdaWorld, an innovative world model learning approach that enables efficient adaptation. The key idea is to incorporate action information duri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18938","kind":"arxiv","version":4},"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/2503.18938/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":"2503.18938","created_at":"2026-07-05T11:14:05.955427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.18938v4","created_at":"2026-07-05T11:14:05.955427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18938","created_at":"2026-07-05T11:14:05.955427+00:00"},{"alias_kind":"pith_short_12","alias_value":"37P2GXVKUFZG","created_at":"2026-07-05T11:14:05.955427+00:00"},{"alias_kind":"pith_short_16","alias_value":"37P2GXVKUFZGRT2M","created_at":"2026-07-05T11:14:05.955427+00:00"},{"alias_kind":"pith_short_8","alias_value":"37P2GXVK","created_at":"2026-07-05T11:14:05.955427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23685","citing_title":"LaST-HD: Learning Latent Physical Reasoning from Scalable Human Data for Robot Manipulation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21139","citing_title":"PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20781","citing_title":"World Action Models: A Survey","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00836","citing_title":"From World Models to World Action Models: A Concise Tutorial for Robotics","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12403","citing_title":"World Pilot: Steering Vision-Language-Action Models with World-Action Priors","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00836","citing_title":"From World Models to World Action Models: A Concise Tutorial for Robotics","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04130","citing_title":"CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04264","citing_title":"UniCanvas: A Diffusion-base Unified Model for Text-in-Image Joint Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01955","citing_title":"WALL-WM: Carving World Action Modeling at the Event Joints","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29059","citing_title":"Flow Matching in Feature Space for Stochastic World Modeling","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17312","citing_title":"VISTA: Triplet-Supervised Video Style Transfer with Diffusion Transformers","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17423","citing_title":"Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19242","citing_title":"PhyWorld: Physics-Faithful World Model for Video Generation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00990","citing_title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11075","citing_title":"RISE: Self-Improving Robot Policy with Compositional World Model","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2510.10125","citing_title":"Ctrl-World: A Controllable Generative World Model for Robot Manipulation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2505.12705","citing_title":"DreamGen: Unlocking Generalization in Robot Learning through Video World Models","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20231","citing_title":"UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10819","citing_title":"ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02911","citing_title":"Learning Task-Invariant Properties via Dreamer: Enabling Efficient Policy Transfer for Quadruped Robots","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2505.06111","citing_title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27448","citing_title":"LA-Pose: Latent Action Pretraining Meets Pose Estimation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10819","citing_title":"ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06298","citing_title":"Render, Don't Decode: Weight-Space World Models with Latent Structural Disentanglement","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01694","citing_title":"Latent State Design for World Models under Sufficiency Constraints","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37P2GXVKUFZGRT2MZSAS73EKLE","json":"https://pith.science/pith/37P2GXVKUFZGRT2MZSAS73EKLE.json","graph_json":"https://pith.science/api/pith-number/37P2GXVKUFZGRT2MZSAS73EKLE/graph.json","events_json":"https://pith.science/api/pith-number/37P2GXVKUFZGRT2MZSAS73EKLE/events.json","paper":"https://pith.science/paper/37P2GXVK"},"agent_actions":{"view_html":"https://pith.science/pith/37P2GXVKUFZGRT2MZSAS73EKLE","download_json":"https://pith.science/pith/37P2GXVKUFZGRT2MZSAS73EKLE.json","view_paper":"https://pith.science/paper/37P2GXVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.18938&json=true","fetch_graph":"https://pith.science/api/pith-number/37P2GXVKUFZGRT2MZSAS73EKLE/graph.json","fetch_events":"https://pith.science/api/pith-number/37P2GXVKUFZGRT2MZSAS73EKLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37P2GXVKUFZGRT2MZSAS73EKLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37P2GXVKUFZGRT2MZSAS73EKLE/action/storage_attestation","attest_author":"https://pith.science/pith/37P2GXVKUFZGRT2MZSAS73EKLE/action/author_attestation","sign_citation":"https://pith.science/pith/37P2GXVKUFZGRT2MZSAS73EKLE/action/citation_signature","submit_replication":"https://pith.science/pith/37P2GXVKUFZGRT2MZSAS73EKLE/action/replication_record"}},"created_at":"2026-07-05T11:14:05.955427+00:00","updated_at":"2026-07-05T11:14:05.955427+00:00"}