AutoDrive-R$^2$: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving

Documenti analoghi

• Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools
  di: Yuan, Zhenlong, et al.
  Pubblicazione: (2025)
• AutoDrive-QA: A Multiple-Choice Benchmark for Vision-Language Evaluation in Urban Autonomous Driving
  di: Khalili, Boshra, et al.
  Pubblicazione: (2025)
• VLM-AutoDrive: Post-Training Vision-Language Models for Safety-Critical Autonomous Driving Events
  di: Bhat, Mohammad Qazim, et al.
  Pubblicazione: (2026)
• Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving
  di: Zhang, Dapeng, 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)