影响力指数

12.88/100

超过 39.7%

全站排名 #38,852

发表论文5 篇

平均评分5.0

年均产出2.5 篇/年

Zhengpeng Xie

PhD student@The Hong Kong University of Science and Technology·中国·OpenReview

研究方向

Reinforcement Learning · Large Language Models · Generative Models

Representation Convergence: Mutual Distillation is Secretly a Form of Regularization

ICLR 2026Withdrawn

Simple Policy Optimization

ICLR 2025Withdrawn

The Meta-Representation Hypothesis

ICML 2025Rejected

A Dual-Agent Adversarial Framework for Generalizable Reinforcement Learning

ICLR 2025Withdrawn

Simple Policy Optimization

ICML 2025Poster

合作者 (8)

Jianxiong Zhang