Reinforcing Action Policies by Prophesying

Jiahui Zhang*, Ze Huang*, Chun Gu, Zipei Ma, Li Zhang†

Project Code

• TL;DR: We introduce ProphRL, which learns a reusable action-to-video world model and a flow-aware RL post-training strategy to improve VLA policies efficiently, delivering strong gains in both simulation and real-robot tasks.

BézierGS: Dynamic Urban Scene Reconstruction with Bézier Curve Gaussian Splatting

Zipei Ma*, Junzhe Jiang*, Yurui Chen, Li Zhang†

Code

• TL;DR: We propose a method that models object motion using Bézier curves, achieving accurate reconstruction and effective foreground-background separation.