{
  "id": 19187,
  "url": "https://arxiv.org/abs/2608.12854v1",
  "title": "BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving",
  "summary": "Autonomous driving requires planning under both semantic constraints and predictive dynamics. Existing end-to-end driving approaches, however, typically emphasize only one side of this requirement: Vision-Language-Action (VLA) models exploit VLM priors for semantic reasoning, while World Action Models (WAMs) provide future-aware prediction through generative world modeling. This naturally motivates a unified planner that can leverage both semantic priors and predictive dynamics. However, we find",
  "authors": "Bing Zhan, Shuyao Shang, Jiahao Gu, Shuo Lu, Yuan Xu, Zhao Wang et al.",
  "category": "research",
  "topics": null,
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-13T05:56:17.000Z",
  "fetched_at": "2026-08-14T05:10:49.168Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/19187",
  "original_url": "https://arxiv.org/abs/2608.12854v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}