影响力指数

0.85/100

超过 1.5%

全站排名 #63,436

发表论文4 篇

平均评分4.1

年均产出1.3 篇/年

Zihan Wang

PhD student@University of California, San Diego·美国·OpenReview

研究方向

Natural language processing · language model · weak supervision

Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks

ICLR 2026Poster

DNAMotifTokenizer: Towards Biologically Informed Tokenization of Genomic Sequences

ICLR 2026Rejected

Model-diff: A Tool for Comparative Study of Language Models in the Input Space

ICLR 2025Withdrawn

合作者 (20)

Niloofar Mireshghallah

Rajesh K. Gupta

Taylor Berg-Kirkpatrick

Earlence Fernandes