ChengpengLi's picture

3 13 2

ChengpengLi

ChengpengLi

·

AI & ML interests

LLM for Reasoning, reinforcement learning, recommendation system, diffusion models

Recent Activity

upvoted a paper 18 days ago

Agentic Entropy-Balanced Policy Optimization

upvoted a paper about 1 month ago

Quantile Advantage Estimation for Entropy-Safe Reasoning

upvoted a paper 3 months ago

We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning

View all activity

Organizations

None yet

Papers 4

arxiv:2503.04625

arxiv:2407.10671

arxiv:2407.04078

arxiv:2406.13542

models 1

ChengpengLi/START

datasets 0

None public yet