影响力指数

12.21/100

超过 37.9%

全站排名 #40,005

发表论文4 篇

平均评分5.3

年均产出2.0 篇/年

Hao Li

PhD student@Washington University, Saint Louis·美国·OpenReview

研究方向

AI safety · Agent Security · LLM Agent · Multimodal Learning

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack

ICLR 2026Withdrawn

DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents

NeurIPS 2025Poster

Debiased Orthogonal Boundary-driven Efficient Noise Mitigation

ICML 2025Rejected

One-step Noisy Label Mitigation

ICLR 2025Withdrawn

合作者 (11)

博士导师2 篇

博士导师2 篇