Fei Wang

Researcher, Google

Joined

June 2021

Names

Fei Wang (Preferred)

Emails

****@gmail.com (Confirmed)

****@usc.edu (Confirmed)

****@google.com (Confirmed)

Personal Links

Career & Education History

Researcher

Google (google.com)

2025 – Present

PhD student

University of Southern California (usc.edu)

2022 – 2025

MS student

University of Southern California (usc.edu)

2020 – 2021

Undergrad student

Renmin University of China (ruc.edu.cn)

2015 – 2019

Advisors, Relations & Conflicts

No relations added

Expertise

natural language processing

Present

language models

Present

machine learning

Present

Publications

Unraveling Indirect In-Context Learning Using Influence Functions
Hadi Askari, Shivanshu Gupta, Terry Tong, Fei Wang, Anshuman Chhabra, Muhao Chen
- Submitted to ICLR 2026
- Readers: Everyone
Unbiased Visual Reasoning with Controlled Visual Inputs
Zhaonan Li, Shijie Lu, Fei Wang, Jacob Dineen, Xiao Ye, Zhikun Xu, Siyi Liu, Young Min Cho, Bangzheng Li, Daniel Chang, Kenny Nguyen, Qizheng Yang, Muhao Chen, Ben Zhou
- Submitted to ICLR 2026
- Readers: Everyone
LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions
Hadi Askari, Shivanshu Gupta, Fei Wang, Anshuman Chhabra, Muhao Chen
- NeurIPS 2025 poster
- Readers: Everyone
Offset Unlearning for Large Language Models
James Y. Huang, Wenxuan Zhou, Fei Wang, Fred Morstatter, Sheng Zhang, Hoifung Poon, Muhao Chen
- Accepted by TMLR
- Readers: Everyone
From Introspection to Best Practices: Principled Analysis of Demonstrations in Multimodal In-Context Learning
Nan Xu, Fei Wang, Sheng Zhang, Hoifung Poon, Muhao Chen
- NAACL (Long Papers) 2025
- Readers: Everyone
Offset Unlearning for Large Language Models
James Y. Huang, Wenxuan Zhou, Fei Wang, Fred Morstatter, Sheng Zhang, Hoifung Poon, Muhao Chen
- Trans. Mach. Learn. Res. 2025
- Readers: Everyone
Aligning to Constraints for Data-Efficient Language Model Customization
Fei Wang, Chao Shang, Shuai Wang, Sarthak Jain, Qiang Ning, Bonan Min, Vittorio Castelli, Yassine Benajiba, Dan Roth
- NAACL (Findings) 2025
- Readers: Everyone
SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment
Qin Liu, Fei Wang, Chaowei Xiao, Muhao Chen
- ACL (1) 2025
- Readers: Everyone
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
Fei Wang, Xingyu Fu, James Y. Huang, Zekun Li, Qin Liu, Xiaogeng Liu, Mingyu Derek Ma, Nan Xu, Wenxuan Zhou, Kai Zhang, Tianyi Lorena Yan, Wenjie Jacky Mo, Hsiang-Hui Liu, Pan Lu, Chunyuan Li, Chaowei Xiao, Kai-Wei Chang, Dan Roth, Sheng Zhang, Hoifung Poon et al. (1 additional authors not shown)
- ICLR 2025
- Readers: Everyone
BadJudge: Backdoor Vulnerabilities of LLM-As-A-Judge
Terry Tong, Fei Wang, Zhe Zhao, Muhao Chen
- ICLR 2025
- Readers: Everyone

View all 48 publications

Co-Authors

View all 140 co-authors