Li Pengyi's picture

Li Pengyi

LiPengyi29

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 16 days ago

Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures

upvoted a paper about 1 month ago

How Far Can Unsupervised RLVR Scale LLM Training?

upvoted a paper 2 months ago

Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities

View all activity

Organizations

Papers 2

arxiv:2506.06395

arxiv:2502.03183

models 1

LiPengyi29/r1-Qwen2.5-vl

Image-Text-to-Text • 8B • Updated Aug 18, 2025

datasets 0

None public yet