WarmPrior: Straightening Flow-Matching Policies with Temporal Priors

Sinjae Kang, Chanyoung Kim, Kaixin Wang, Li Zhao, Kimin Lee

Keywords: Flow Matching Policies, Temporally Grounded Prior, Trajectory Straightening, Robotic Manipulation, Prior-Space Reinforcement Learning

TL;DR: Replace the standard N(0, I) source in flow-matching policies with a temporally grounded prior from recent action history, straightening paths and improving both behavior cloning success rates and prior-space RL efficiency in robotic manipulation.

Abstract: Generative policies based on diffusion and flow matching have become a dominant paradigm for visuomotor robotic control. We show that replacing the standard Gaussian source distribution with **WarmPrior**, a simple temporally grounded prior constructed from readily available recent action history, consistently improves success rates on robotic manipulation tasks. We trace this gain to markedly *straighter* probability paths, echoing the effect of optimal-transport couplings in Rectified Flow. Beyond standard behavior cloning, **WarmPrior** also reshapes the exploration distribution in prior-space reinforcement learning, improving both sample efficiency and final performance. Collectively, these results identify the *source distribution* as an important and underexplored design axis in generative robot control.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 77