影响力指数

31.54/100

前 22.7%

全站排名 #14,638

发表论文5 篇

平均评分4.5

年均产出2.5 篇/年

Wei Zhao

PhD student@Singapore Management University·OpenReview

研究方向

Large Language Model · Computer Vision

Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing

ICLR 2026Poster

AutoBackdoor: Automating Backdoor Attacks via LLM Agents

ICLR 2026Rejected

Democratic Training Against Universal Adversarial Perturbations

ICLR 2025Poster

Adversarial Suffixes May Be Features Too!

ICLR 2025Withdrawn

Do Influence Functions Work on Large Language Models?

ICLR 2025Withdrawn

合作者 (7)

博士导师5 篇