Scholar
Zhanhui Zhou
Google Scholar ID: SbACfYQAAAAJ
UC Berkeley
Citations & Impact
Citations
532
H-index
7
i10-index
6
Publications
9
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Published multiple papers including but not limited to 'VLMs Can Aggregate Scattered Training Patches' (NeurIPS 2025), 'Emergent Response Planning in LLMs' (ICML 2025), etc. Among them, 'Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!' won the Outstanding Paper Award at ACL 2024.
Research Experience
- Conducting research as a CS Ph.D. student at UC Berkeley.
Education
- Dual bachelor's degrees from University of Michigan (UMich) and Shanghai Jiao Tong University (SJTU). Currently, a first-year CS Ph.D. student at UC Berkeley.
Background
- Research Interests: Human-centered AI; Focus Areas: Developing scalable algorithms that align language models with human values and interactive systems that enhance human experiences by leveraging stronger language models and continuously improving through human interaction.
Co-authors