3 papers
cs.RO2026
FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation
Shuyi Zhang, Yunfan Lou, Hongyang Cheng +8
Vision-Language-Action (VLA) models are often constrained by the imitation ceiling imposed by sub-optimal data. While Reinforcement Learning (RL) fine-tuning can surpass this limit…
cs.RO2026
ProDrive: Proactive Planning for Autonomous Driving via Ego-Environment Co-Evolution
Chuyao Fu, Shengzhe Gan, Zhuoli Ouyang +5
End-to-end autonomous driving planners typically generate trajectories from current observations alone. However, real-world driving is highly dynamic, and such reactive planning ca…
cs.RO2026
Mask World Model: Predicting What Matters for Robust Robot Policy Learning
Yunfan Lou, Xiaowei Chi, Xiaojie Zhang +9
World models derived from large-scale video generative pre-training have emerged as a promising paradigm for generalist robot policy learning. However, standard approaches often fo…