Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
AdvantageFlow: Advantage-Weighted Least Squares for RL in Flow Models
Branislav Kveton, Anup Rao, Subhojyoti Mukherjee +2
We introduce AdvantageFlow, a forward-process reinforcement learning algorithm for rectified flow models. Unlike Flow-GRPO, which optimizes the reverse process, we optimize an adva…
cs.LG2026
Stepwise Credit Assignment for GRPO on Flow-Matching Models
Yash Savani, Branislav Kveton, Yuchen Liu +5
Flow-GRPO successfully applies reinforcement learning to flow models, but uses uniform credit assignment across all steps. This ignores the temporal structure of diffusion generati…