Zihan Wang

PhD student, Computer Science, University of California, San Diego

Joined

September 2019

Names

Zihan Wang (Preferred)

Emails

****@illinois.edu (Confirmed)

****@ucsd.edu (Confirmed)

****@anthropic.com (Confirmed)

Personal Links

Career & Education History

PhD student

Computer Science, University of California, San Diego (ucsd.edu)

2020 – 2026

Undergrad student

Computer Science, University of Illinois, Urbana Champaign (illinois.edu)

2016 – 2020

Advisors, Relations & Conflicts

No relations added

Expertise

Natural language processing

Present

language model

Present

weak supervision

Present

Publications

DNAMotifTokenizer: Towards Biologically Informed Tokenization of Genomic Sequences
Xiaoxiao Zhou, Zihan Wang, Jingbo Shang, Yang E. Li
- Submitted to ICLR 2026
- Readers: Everyone
Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
Hoagy Cunningham, Jerry Wei, Zihan Wang, Andrew Persic, Alwin Peng, Jordan Abderrachid, Raj Agarwal, Bobby Chen, Andy Dau, Alek Dimitriev, Logan Howard, Yijin Hua, Rob Gilson, Mu Lin, Christopher Liu, Vladimir Mikulik, Rohit Mittapalli, Clare O'Hara, Jin Pan, Nikhil Saxena et al. (7 additional authors not shown)
- ICLR 2026 Poster
- Readers: Everyone
OmniInput: An Evaluation Framework for Deep Learning Models on Internet-Scale Data
Weitang Liu, Yuelei Li, Ying Wai Li, Zihan Wang, Yi-Zhuang You, Jingbo Shang
- Accepted by TMLR
- Readers: Everyone
Model-diff: A Tool for Comparative Study of Language Models in the Input Space
Weitang Liu, Yuelei Li, Zihan Wang, Ying Wai Li, Jingbo Shang
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
WavSpA: Wavelet Space Attention for Boosting Transformers' Long Sequence Learning Ability
Yufan Zhuang, Zihan Wang, Fangbo Tao, Jingbo Shang
- UniReps Poster
- Readers: Everyone
How Few Davids Improve One Goliath: Federated Learning in Resource-Skew Edge Computing Environments
Jiayun Zhang, Shuheng Li, Haiyu Huang, Zihan Wang, Xiaohan Fu, Dezhi Hong, Rajesh K. Gupta, Jingbo Shang
- TheWebConf24 Oral
- Readers: Everyone
Misusing Tools in Large Language Models With Visual Adversarial Examples
Xiaohan Fu, Zihan Wang, Shuheng Li, Rajesh K. Gupta, Niloofar Mireshghallah, Taylor Berg-Kirkpatrick, Earlence Fernandes
- Submitted to ICLR 2024
- Readers: Everyone
ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation
Zi Lin, Zihan Wang, Yongqi Tong, Yangkun Wang, Yuxin Guo, Yujia Wang, Jingbo Shang
- EMNLP 2023 Findings
- Readers: Everyone
Debiasing Made State-of-the-art: Revisiting the Simple Seed-based Weak Supervision for Text Classification
Chengyu Dong, Zihan Wang, Jingbo Shang
- EMNLP 2023 Main
- Readers: Everyone
Goal-Driven Explainable Clustering via Language Descriptions
Zihan Wang, Jingbo Shang, Ruiqi Zhong
- EMNLP 2023 Main
- Readers: Everyone

View all 32 publications

Co-Authors

View all 82 co-authors