影响力指数

-/100

发表论文3 篇

平均评分3.6

年均产出3.0 篇/年

XIANGLIN YANG

Postdoc@National University of Singapore·新加坡·OpenReview

研究方向

LLM Safety · Trustworthy AI · Data Visualization · Dimension Reduction

Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges

ICLR 2026Rejected

Beyond Manuals and Tasks: Instance-Level Context Learning for LLM Agents

ICLR 2026Withdrawn

Turning Shields into Swords: Leveraging Safety Policies for LLM Safety Testing

ICLR 2026Withdrawn

合作者 (14)

博后导师2 篇