{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PCXC2ZVCJZRC2DT6HPFORV2BA6","short_pith_number":"pith:PCXC2ZVC","schema_version":"1.0","canonical_sha256":"78ae2d66a24e622d0e7e3bcae8d74107b7cedc81be38f4f030e569b751646774","source":{"kind":"arxiv","id":"2310.10625","version":1},"attestation_state":"computed","paper":{"title":"Video Language Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Andy Zeng, Ayzaan Wahid, Brian Ichter, Fei Xia, Jonathan Tompson, Joshua B. Tenenbaum, Leslie Kaelbling, Mengjiao Yang, Pete Florence, Pierre Sermanet, Pieter Abbeel, Tianhe Yu, Yilun Du","submitted_at":"2023-10-16T17:48:45Z","abstract_excerpt":"We are interested in enabling visual planning for complex long-horizon tasks in the space of generated videos and language, leveraging recent advances in large generative models pretrained on Internet-scale data. To this end, we present video language planning (VLP), an algorithm that consists of a tree search procedure, where we train (i) vision-language models to serve as both policies and value functions, and (ii) text-to-video models as dynamics models. VLP takes as input a long-horizon task instruction and current image observation, and outputs a long video plan that provides detailed mul"},"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":"2310.10625","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-16T17:48:45Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"9796c6ad2cdd85059bfaa40dc8c97072c526a6b2261a041dac9308252f681991","abstract_canon_sha256":"35e518b7d2a8d9cf8cf6fe901380afec54654a0fafc9f27ee83f3a4a4c6b1173"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:22.527521Z","signature_b64":"pEu8prYa4NTXk4tfT4PKxeixCag2nedrA6ozFK2wVVkuaENv49QtFNfA+0KP66UiLCxClPax5lw3KQ2O57JLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78ae2d66a24e622d0e7e3bcae8d74107b7cedc81be38f4f030e569b751646774","last_reissued_at":"2026-07-05T07:01:22.527006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:22.527006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Language Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Andy Zeng, Ayzaan Wahid, Brian Ichter, Fei Xia, Jonathan Tompson, Joshua B. Tenenbaum, Leslie Kaelbling, Mengjiao Yang, Pete Florence, Pierre Sermanet, Pieter Abbeel, Tianhe Yu, Yilun Du","submitted_at":"2023-10-16T17:48:45Z","abstract_excerpt":"We are interested in enabling visual planning for complex long-horizon tasks in the space of generated videos and language, leveraging recent advances in large generative models pretrained on Internet-scale data. To this end, we present video language planning (VLP), an algorithm that consists of a tree search procedure, where we train (i) vision-language models to serve as both policies and value functions, and (ii) text-to-video models as dynamics models. VLP takes as input a long-horizon task instruction and current image observation, and outputs a long video plan that provides detailed mul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10625","kind":"arxiv","version":1},"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/2310.10625/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":"2310.10625","created_at":"2026-07-05T07:01:22.527067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10625v1","created_at":"2026-07-05T07:01:22.527067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10625","created_at":"2026-07-05T07:01:22.527067+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCXC2ZVCJZRC","created_at":"2026-07-05T07:01:22.527067+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCXC2ZVCJZRC2DT6","created_at":"2026-07-05T07:01:22.527067+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCXC2ZVC","created_at":"2026-07-05T07:01:22.527067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.06522","citing_title":"Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06559","citing_title":"RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20781","citing_title":"World Action Models: A Survey","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01166","citing_title":"Structured 4D Latent Predictive Model for Robot Planning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03868","citing_title":"Unified Video-Action Joint Denoising for Dexterous Action and Data Generation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22882","citing_title":"GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.15032","citing_title":"How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30346","citing_title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22882","citing_title":"GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16054","citing_title":"Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00990","citing_title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":151,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01925","citing_title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","ref_index":158,"is_internal_anchor":false},{"citing_arxiv_id":"2512.15840","citing_title":"Large Video Planner Enables Generalizable Robot Control","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04447","citing_title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2601.07060","citing_title":"PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2409.01652","citing_title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2503.22020","citing_title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2508.00795","citing_title":"Video Generators are Robot Policies","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2512.15692","citing_title":"mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14274","citing_title":"CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03066","citing_title":"Redefining End-of-Life: Intelligent Automation for Electronics Remanufacturing Systems","ref_index":184,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11367","citing_title":"3D-Belief: Embodied Belief Inference via Generative 3D World Modeling","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06158","citing_title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCXC2ZVCJZRC2DT6HPFORV2BA6","json":"https://pith.science/pith/PCXC2ZVCJZRC2DT6HPFORV2BA6.json","graph_json":"https://pith.science/api/pith-number/PCXC2ZVCJZRC2DT6HPFORV2BA6/graph.json","events_json":"https://pith.science/api/pith-number/PCXC2ZVCJZRC2DT6HPFORV2BA6/events.json","paper":"https://pith.science/paper/PCXC2ZVC"},"agent_actions":{"view_html":"https://pith.science/pith/PCXC2ZVCJZRC2DT6HPFORV2BA6","download_json":"https://pith.science/pith/PCXC2ZVCJZRC2DT6HPFORV2BA6.json","view_paper":"https://pith.science/paper/PCXC2ZVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10625&json=true","fetch_graph":"https://pith.science/api/pith-number/PCXC2ZVCJZRC2DT6HPFORV2BA6/graph.json","fetch_events":"https://pith.science/api/pith-number/PCXC2ZVCJZRC2DT6HPFORV2BA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCXC2ZVCJZRC2DT6HPFORV2BA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCXC2ZVCJZRC2DT6HPFORV2BA6/action/storage_attestation","attest_author":"https://pith.science/pith/PCXC2ZVCJZRC2DT6HPFORV2BA6/action/author_attestation","sign_citation":"https://pith.science/pith/PCXC2ZVCJZRC2DT6HPFORV2BA6/action/citation_signature","submit_replication":"https://pith.science/pith/PCXC2ZVCJZRC2DT6HPFORV2BA6/action/replication_record"}},"created_at":"2026-07-05T07:01:22.527067+00:00","updated_at":"2026-07-05T07:01:22.527067+00:00"}