arxiv:2504.00891
Jiafei Lyu
dmux
AI & ML interests
Reinforcement Learning
Recent Activity
authored
a paper
1 day ago
GenPRM: Scaling Test-Time Compute of Process Reward Models via
Generative Reasoning
authored
a paper
11 months ago
SEABO: A Simple Search-Based Method for Offline Imitation Learning
authored
a paper
over 1 year ago
Using Human Feedback to Fine-tune Diffusion Models without Any Reward
Model
Organizations
