{"paper":{"title":"Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Driver-WM forecasts in-cabin driver dynamics by causally conditioning on out-cabin traffic in a compact latent space.","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chen Lv, Daosheng Qiu, Haochen Liu, Haoruo Zhang, Hao Su, Haozhuang Chi, Zirui Li","submitted_at":"2026-05-06T16:30:48Z","abstract_excerpt":"Safe L2/L3 driving automation requires anticipating human-in-the-loop reactions during shared-control transitions. While most driving world models forecast the external environment, in-cabin intelligence remains strictly recognition-oriented and lacks multi-step rollout capabilities for driver dynamics. We introduce Driver-WM, a driver-centric latent world model that rolls out in-cabin dynamics causally conditioned on out-cabin traffic context. This formulation unifies physical kinematics forecasting with auxiliary behavioral and emotional semantic recognition. Operating in a compact latent sp"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Driver-WM yields robust long-horizon geometric forecasting for reactive high-motion maneuvers and improves semantic alignment for both driver and traffic states.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a compact latent space constructed from frozen vision-language features, combined with the dual-stream gated causal injection, is sufficient to capture and causally link external traffic context to internal driver dynamics without critical information loss.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Driver-WM rolls out in-cabin driver states in a compact latent space from frozen vision-language features, using traffic-conditioned dual streams and gated causal injection for long-horizon geometric and semantic forecasting.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Driver-WM forecasts in-cabin driver dynamics by causally conditioning on out-cabin traffic in a compact latent space.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7d4991755bf28071f1cd0fcf359fc72afc6ed0ac7b5042349dca3897c2776759"},"source":{"id":"2605.05092","kind":"arxiv","version":2},"verdict":{"id":"4595c1de-029e-45a9-8fb6-9b2b5de6d791","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T16:47:19.544373Z","strongest_claim":"Driver-WM yields robust long-horizon geometric forecasting for reactive high-motion maneuvers and improves semantic alignment for both driver and traffic states.","one_line_summary":"Driver-WM rolls out in-cabin driver states in a compact latent space from frozen vision-language features, using traffic-conditioned dual streams and gated causal injection for long-horizon geometric and semantic forecasting.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a compact latent space constructed from frozen vision-language features, combined with the dual-stream gated causal injection, is sufficient to capture and causally link external traffic context to internal driver dynamics without critical information loss.","pith_extraction_headline":"Driver-WM forecasts in-cabin driver dynamics by causally conditioning on out-cabin traffic in a compact latent space."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.05092/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T10:37:46.228715Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.613152Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T13:50:14.315016Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ed67713cc2812ca30dba7727eea7a9d60fd9cc5a8aca9a270846bad383133d80"},"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"}