影响力指数

18.13/100

前 46.1%

全站排名 #29,689

发表论文2 篇

平均评分5.0

年均产出2.0 篇/年

Sihui Dai

Researcher@CapitalOne·美国·OpenReview

研究方向

adversarial robustness · trustworthy ai · reasoning · alignment

Adapting to Evolving Adversaries with Regularized Continual Robust Training

ICML 2025Poster

MEMREASONER: A MEMORY-AUGMENTED LANGUAGE MODEL ARCHITECTURE FOR MULTI-HOP REASONING

ICLR 2025Rejected

合作者 (9)

Georgios Kollias

Subhajit Chaudhury

Christian Cianfarani

博士导师1 篇