AI RESEARCH
Manifold-Aware Exploration for Reinforcement Learning in Video Generation
arXiv CS.AI
•
ArXi:2603.21872v1 Announce Type: cross Group Relative Policy Optimization (GRPO) methods for video generation like FlowGRPO remain far less reliable than their counterparts for language models and images. This gap arises because video generation has a complex solution space, and the ODE-to-SDE conversion used for exploration can inject excess noise, lowering rollout quality and making reward estimates less reliable, which destabilizes post-