VLM-AutoDrive: Post-Training Vision-Language Models for Safety-Critical Autonomous Driving Events

Documenti analoghi

• AutoDrive-QA: A Multiple-Choice Benchmark for Vision-Language Evaluation in Urban Autonomous Driving
  di: Khalili, Boshra, et al.
  Pubblicazione: (2025)
• AutoDrive-R$^2$: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving
  di: Yuan, Zhenlong, et al.
  Pubblicazione: (2025)
• DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
  di: Tian, Xiaoyu, et al.
  Pubblicazione: (2024)
• CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Models
  di: Sheng, Zihao, et al.
  Pubblicazione: (2025)
• $AutoDrive\text{-}P^3$: Unified Chain of Perception-Prediction-Planning Thought via Reinforcement Fine-Tuning
  di: Ye, Yuqi, et al.
  Pubblicazione: (2026)