影响力指数

-/100

发表论文2 篇

平均评分4.4

年均产出1.0 篇/年

Pankayaraj Pathmanathan

PhD student@University of Maryland, College Park·美国·OpenReview

Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward Modeling

ICLR 2026Withdrawn

AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment

ICLR 2025Rejected

合作者 (3)

博士导师2 篇

Michael-Andrei Panaitescu-Liess

Udari Madhushani Sehwag