一作NeurIPS 2026Poster
PRECISE: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models
Bo Peng · Tao Huang · Weijie Kong · Junzhe Li · Yue Wu · Qi Tian · Jiangfeng Xiong · Jian-Wei Zhang · Liefeng Bo · Zhao Zhong
强化学习与后训练OpenReview