AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
机构 * University of California, Los Angeles(加州大学洛杉矶分校)
专题命中 VLA模型 :vision-language-action(title,abstract);action model(title);VLA(abstract);分类 cs.CV
Comments NeurIPS 2025; Website link:https://autovla.github.io/