Embodied AI

Generative policies

• Preprint · 2026

  Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent

  Zeyuan Wang, Da Li, Yulin Chen, Yuehu Gong, Yanming Guo, Ye Shi, Liang Bai, Tianyuan Yu, Yanwei Fu

  Efficient generative policies for exploration and stable off-policy reinforcement learning.

• AAAI 2026

  One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow

  Zeyuan Wang, Da Li, Yulin Chen, Ye Shi, Liang Bai, Tianyuan Yu, Yanwei Fu

  A one-step generative policy for offline and offline-to-online reinforcement learning.