{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7DS6TEBOUDI5YDK5BNEM5WPYOF","short_pith_number":"pith:7DS6TEBO","schema_version":"1.0","canonical_sha256":"f8e5e9902ea0d1dc0d5d0b48ced9f871534ff7349fa93898aa9bb664bc9abd99","source":{"kind":"arxiv","id":"2502.15672","version":1},"attestation_state":"computed","paper":{"title":"VaViM and VaVAM: Autonomous Driving through Video Generative Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexandre Boulch, Andrei Bursuc, David Hurych, Eduardo Valle, Elias Ramzi, \\'Eloi Zablocki, Florent Bartoccioni, Loick Chambon, Matthieu Cord, Mickael Chen, Renaud Marlet, Serkan Odabas, Shashanka Venkataramanan, Spyros Gidaris, Tuan-Hung Vu, Victor Besnier, Yihong Xu","submitted_at":"2025-02-21T18:56:02Z","abstract_excerpt":"We explore the potential of large-scale generative video models for autonomous driving, introducing an open-source auto-regressive video model (VaViM) and its companion video-action model (VaVAM) to investigate how video pre-training transfers to real-world driving. VaViM is a simple auto-regressive video model that predicts frames using spatio-temporal token sequences. We show that it captures the semantics and dynamics of driving scenes. VaVAM, the video-action model, leverages the learned representations of VaViM to generate driving trajectories through imitation learning. Together, the mod"},"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":"2502.15672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-21T18:56:02Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"252affcc5a8f8486a399891d938d308cdb69c73adaa274e81d9fe28d4df7aa15","abstract_canon_sha256":"3167398f99c123852e61a8f0463a657f07a5da0b38cf8d575f18212413c90e1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:05.508453Z","signature_b64":"twnkOm8QGw/DG5ef4wxmYKi2ZMzhz9OIAtZuuetKRdTSfpP0RXHF74FvIb2DcTT/WvZMf6rjWBOU/fnwELa7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8e5e9902ea0d1dc0d5d0b48ced9f871534ff7349fa93898aa9bb664bc9abd99","last_reissued_at":"2026-07-05T10:18:05.507974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:05.507974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VaViM and VaVAM: Autonomous Driving through Video Generative Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexandre Boulch, Andrei Bursuc, David Hurych, Eduardo Valle, Elias Ramzi, \\'Eloi Zablocki, Florent Bartoccioni, Loick Chambon, Matthieu Cord, Mickael Chen, Renaud Marlet, Serkan Odabas, Shashanka Venkataramanan, Spyros Gidaris, Tuan-Hung Vu, Victor Besnier, Yihong Xu","submitted_at":"2025-02-21T18:56:02Z","abstract_excerpt":"We explore the potential of large-scale generative video models for autonomous driving, introducing an open-source auto-regressive video model (VaViM) and its companion video-action model (VaVAM) to investigate how video pre-training transfers to real-world driving. VaViM is a simple auto-regressive video model that predicts frames using spatio-temporal token sequences. We show that it captures the semantics and dynamics of driving scenes. VaVAM, the video-action model, leverages the learned representations of VaViM to generate driving trajectories through imitation learning. Together, the mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15672","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/2502.15672/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":"2502.15672","created_at":"2026-07-05T10:18:05.508031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.15672v1","created_at":"2026-07-05T10:18:05.508031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15672","created_at":"2026-07-05T10:18:05.508031+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DS6TEBOUDI5","created_at":"2026-07-05T10:18:05.508031+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DS6TEBOUDI5YDK5","created_at":"2026-07-05T10:18:05.508031+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DS6TEBO","created_at":"2026-07-05T10:18:05.508031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21172","citing_title":"BadDreamer: Transferable Backdoor Attacks against Video World Models for Autonomous Driving","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05645","citing_title":"Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01164","citing_title":"Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends","ref_index":209,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00267","citing_title":"StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27504","citing_title":"ReWorld: Learning Better Representations for World Action Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28544","citing_title":"DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2512.24497","citing_title":"What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18074","citing_title":"4DLidarOpen: An Open 4D FMCW Lidar Dataset for Motion-Aware Autonomous Driving","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2510.12796","citing_title":"DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23421","citing_title":"DriveLaW:Unifying Planning and Video Generation in a Latent Driving World","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":196,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11550","citing_title":"The DAWN of World-Action Interactive Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11707","citing_title":"Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DS6TEBOUDI5YDK5BNEM5WPYOF","json":"https://pith.science/pith/7DS6TEBOUDI5YDK5BNEM5WPYOF.json","graph_json":"https://pith.science/api/pith-number/7DS6TEBOUDI5YDK5BNEM5WPYOF/graph.json","events_json":"https://pith.science/api/pith-number/7DS6TEBOUDI5YDK5BNEM5WPYOF/events.json","paper":"https://pith.science/paper/7DS6TEBO"},"agent_actions":{"view_html":"https://pith.science/pith/7DS6TEBOUDI5YDK5BNEM5WPYOF","download_json":"https://pith.science/pith/7DS6TEBOUDI5YDK5BNEM5WPYOF.json","view_paper":"https://pith.science/paper/7DS6TEBO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.15672&json=true","fetch_graph":"https://pith.science/api/pith-number/7DS6TEBOUDI5YDK5BNEM5WPYOF/graph.json","fetch_events":"https://pith.science/api/pith-number/7DS6TEBOUDI5YDK5BNEM5WPYOF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DS6TEBOUDI5YDK5BNEM5WPYOF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DS6TEBOUDI5YDK5BNEM5WPYOF/action/storage_attestation","attest_author":"https://pith.science/pith/7DS6TEBOUDI5YDK5BNEM5WPYOF/action/author_attestation","sign_citation":"https://pith.science/pith/7DS6TEBOUDI5YDK5BNEM5WPYOF/action/citation_signature","submit_replication":"https://pith.science/pith/7DS6TEBOUDI5YDK5BNEM5WPYOF/action/replication_record"}},"created_at":"2026-07-05T10:18:05.508031+00:00","updated_at":"2026-07-05T10:18:05.508031+00:00"}