Zikui Cai

Postdoc, University of Maryland, College Park

Joined

March 2020

Names

Zikui Cai (Preferred)

Emails

****@ucr.edu (Confirmed)

****@umd.edu (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Postdoc

University of Maryland, College Park (umd.edu)

2024 – Present

PhD student

University of California, Riverside (ucr.edu)

2020 – 2024

Advisors, Relations & Conflicts

Postdoc Advisor

Furong Huang

2024 – Present

Postdoc Advisor

Tom Goldstein

2024 – Present

PhD Advisor

M. Salman Asif

2020 – 2024

Expertise

Robotics

2025 – Present

Trustworthy machine learning

2020 – Present

Computer vision

2020 – Present

Publications

TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos
Seungjae Lee, Yoonkyo Jung, Inkook Chun, Yao-Chih Lee, Zikui Cai, Hongjia Huang, Aayush Talreja, Tan Dat Dao, Yongyuan Liang, Jia-Bin Huang, Furong Huang
- OpenReview Archive Direct Upload
- Readers: Everyone
The Low-Frequency Trap: Why Scaling Doesn't Solve Simple Temporal Counting
Sarvesh Baskar, Muhammad R. Islam, Zikui Cai, Ankit Nakhawa, Anirudh Satheesh, Tom Goldstein, Furong Huang
- ICLR 2026 Workshop ICBINB
- Readers: Everyone
AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security
Zikui Cai, Shayan Shabihi, Bang An, Zora Che, Brian R. Bartoldson, Bhavya Kailkhura, Tom Goldstein, Furong Huang
- Submitted to ICLR 2026
- Readers: Everyone
Zebra-CoT: A Dataset for Interleaved Vision-Language Reasoning
Ang Li, Charles L. Wang, Deqing Fu, Kaiyu Yue, Zikui Cai, Wang Bill Zhu, Ollie Liu, Peng Guo, Willie Neiswanger, Furong Huang, Tom Goldstein, Micah Goldblum
- ICLR 2026 Poster
- Readers: Everyone
MORSE: A Suite of Programmatically Controllable Multimodal Reasoning Environments with Steerable Difficulty
Zikui Cai, Andrew Wang, Anirudh Satheesh, Ankit Nakhawa, Hyunwoo Jae, Keenan Powell, Minghui Liu, Neel Jay, Sungbin Oh, Xiyao Wang, Yongyuan Liang, Tom Goldstein, Furong Huang
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
Zora Che, Stephen Casper, Robert Kirk, Anirudh Satheesh, Stewart Slocum, Lev E McKinney, Rohit Gandikota, Aidan Ewart, Domenic Rosati, Zichu Wu, Zikui Cai, Bilal Chughtai, Yarin Gal, Furong Huang, Dylan Hadfield-Menell
- Accepted by TMLR
- Readers: Everyone
AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security
Zikui Cai, Shayan Shabihi, Bang An, Zora Che, Brian R. Bartoldson, Bhavya Kailkhura, Tom Goldstein, Furong Huang
- BuildingTrust
- Readers: Everyone
Targeted Unlearning with Single Layer Unlearning Gradient
Zikui Cai, Yaoteng Tan, M. Salman Asif
- ICML 2025 poster
- Readers: Everyone
Model Manipulation Attacks Enable More Rigorous Evaluations of LLM Capabilities
Zora Che, Stephen Casper, Anirudh Satheesh, Rohit Gandikota, Domenic Rosati, Stewart Slocum, Lev E McKinney, Zichu Wu, Zikui Cai, Bilal Chughtai, Daniel Filan, Furong Huang, Dylan Hadfield-Menell
- SafeGenAi Poster
- Readers: Everyone
Targeted Unlearning with Single Layer Unlearning Gradient
Zikui Cai, Yaoteng Tan, M. Salman Asif
- SafeGenAi Poster
- Readers: Everyone

View all 23 publications

Co-Authors

View all 61 co-authors