影响力指数

8.41/100

超过 26.2%

全站排名 #47,531

发表论文3 篇

平均评分4.3

年均产出1.5 篇/年

Hengguang Zhou

PhD student@University of California, Los Angeles·美国·OpenReview

研究方向

Large Language Model Safety · Large Language Model

VisualThinker: First ever R1-Zero's Aha Moment on just a 2B non-SFT Model

ICLR 2026Rejected

Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods?

ICLR 2026Withdrawn

Is Your Multimodal Language Model Oversensitive to Safe Queries?

ICLR 2025Poster

合作者 (10)

博士导师3 篇