3 papers
cs.CV2026
Simplifying and Improving On-Policy Distillation for Few-Step Diffusion
Jiawei Zhang, Ziyu Wan, Nanye Ma +5
Few-step distillation reduces the sampling cost of diffusion and flow models, but existing approaches often require auxiliary score models or specialized architectures. We show tha…
cs.RO2026
RE-0: Verified Recursive Improvement of Embodied Code-as-Policy Agents through Local On-Policy Distillation
Jiawei Zhang, Xiangrong Zhang, Rui Song +3
Code-as-Policy agents accomplish long-horizon embodied tasks by generating and executing code, yet continually improving them with teachers that are stronger but not globally relia…
cs.RO2026
PACE: Phase-Progress-Aware Credit for Long-Horizon Embodied Manipulation
Chengye Song, Jiawei Zhang, Rui Song +5
Post-training of vision-language-action (VLA) models typically relies on expert demonstrations and policy interaction trajectories. However, in long-horizon manipulation, a single…