Yujin Potter

Postdoc, Department of Electrical Engineering and Computer Sciences, University of California, Berkeley

Joined

January 2024

Names

Yujin Potter (Preferred)

Emails

****@berkeley.edu (Confirmed)

****@gmail.com

Personal Links

Google Scholar

Career & Education History

Postdoc

Department of Electrical Engineering and Computer Sciences, University of California, Berkeley (berkeley.edu)

2022 – Present

Advisors, Relations & Conflicts

Postdoc Advisor

Dawn Song

Present

PhD Advisor

Yongdae Kim

Present

Expertise

AI safety

Present

AI societal impact

Present

Publications

LLM Agentic System Safety Requires Hybrid Alignment
Vincent Siu, Kyle Montgomery, Yujin Potter, Zhun Wang, Dawn Song, Chenguang Wang
- ICLR 2026 AIWILD
- Readers: Everyone
Agents in the Wild: Safety, Security, and Beyond
Dawn Song, Chenguang Wang, Nicholas Crispino, Ruoxi Jia, Kyle Montgomery, Yujin Potter, Vincent Siu, Zhun Wang
- ICLR 2026 Workshop Proposals
- Readers: Everyone
Investigating the Link Between Representational Similarity and Model Interactions
Yujin Potter, Seun Eisape, Shiyang Lai, Alexander Huth, James Evans, Been Kim, Jacob Eisenstein, Dawn Song, Alane Suhr
- Submitted to ICLR 2026
- Readers: Everyone
Biased AI Improves Human Decision-Making But Reduces Trust
Shiyang Lai, Junsol Kim, Nadav Kunievsky, Yujin Potter, James Evans
- ACA-NeurIPS2025 Poster
- Readers: Everyone
VMDT: Decoding the Trustworthiness of Video Foundation Models
Yujin Potter, Zhun Wang, Nicholas Crispino, Kyle Montgomery, Alexander Xiong, Ethan Y. Chang, Francesco Pinto, Yuqi Chen, Rahul Gupta, Morteza Ziyadi, Christos Christodoulopoulos, Bo Li, Chenguang Wang, Dawn Song
- NeurIPS 2025 Datasets and Benchmarks Track poster
- Readers: Everyone
Position: Political Neutrality in AI Is Impossible — But Here Is How to Approximate It
Jillian Fisher, Ruth Elisabeth Appel, Chan Young Park, Yujin Potter, Liwei Jiang, Taylor Sorensen, Shangbin Feng, Yulia Tsvetkov, Margaret Roberts, Jennifer Pan, Dawn Song, Yejin Choi
- ICML 2025 Position Paper Track oral
- Readers: Everyone
LLMs' Potential Influences on Our Democracy: Challenges and Opportunities
Yujin Potter, David Rand, Yejin Choi, Dawn Song
- ICLR 2025 Blogpost Track
- Readers: Everyone
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
Chejian Xu, Jiawei Zhang, Zhaorun Chen, Chulin Xie, Mintong Kang, Yujin Potter, Zhun Wang, Zhuowen Yuan, Alexander Xiong, Zidi Xiong, Chenhui Zhang, Lingzhi Yuan, Yi Zeng, Peiyang Xu, Chengquan Guo, Andy Zhou, Jeffrey Ziwei Tan, Xuandong Zhao, Francesco Pinto, Zhen Xiang et al. (5 additional authors not shown)
- ICLR 2025 Poster
- Readers: Everyone
Position: Evolving AI Collectives Enhance Human Diversity and Enable Self-Regulation
Shiyang Lai, Yujin Potter, Junsol Kim, Richard Zhuang, Dawn Song, James Evans
- ICML 2024 Poster
- Readers: Everyone

Co-Authors

View all 55 co-authors