Jiafei Lyu's picture

1

Jiafei Lyu

dmux

·

https://dmksjfl.github.io/

dmksjfl

AI & ML interests

Reinforcement Learning

Recent Activity

upvoted a paper 18 days ago

EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control

authored a paper 8 months ago

GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning

authored a paper over 1 year ago

SEABO: A Simple Search-Based Method for Offline Imitation Learning

View all activity

Organizations

Papers 3

arxiv:2504.00891

arxiv:2402.03807

arxiv:2311.13231

models 0

None public yet

datasets 0

None public yet