Author

Shangzhe Li

Observed name: Li, Shangzhe

Institution: University of North Carolina at Chapel Hill

Observed institution: University of North Carolina at Chapel Hill

OpenAlex ID: A5153429193

Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It

2026 · Yu, Tianrun, Zhao, Kaixiang, et al. · arXiv (Cornell University) · 1

An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning

2026 · Li, Shangzhe, Yang, Yuxiao, et al. · arXiv (Cornell University)

Provable Benefits of Regularization: Fast Rates for Adversarial Imitation Learning

2026 · Zhou, Hanbin, Li, Shangzhe, et al. · arXiv (Cornell University)

Works count: 3

Citation count: 1

H-index: 1

I10-index: