Jing-Zhe Shi

Timestep Weighting: A Hidden Key to Effective ELBO-Based Flow-Matching RL

ELBO-based reinforcement learning offers a sampler-agnostic approach to fine-tuning flow matching models with reward feedback. Timestep weighting in ELBO-based RL has large impact on performance, and it also provides a unified view (as we show in this work) to understand prediction losses heuristically chosen in prior...