{
  "id": 4898,
  "url": "https://arxiv.org/abs/2605.05092v2",
  "title": "Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout",
  "summary": "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 foreca",
  "authors": "Haozhuang Chi, Daosheng Qiu, Hao Su, Haochen Liu, Zirui Li, Haoruo Zhang et al.",
  "category": "research",
  "topics": "jobs-economy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-06T16:30:48.000Z",
  "fetched_at": "2026-07-14T16:31:21.932Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4898",
  "original_url": "https://arxiv.org/abs/2605.05092v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}