Scholar
Sicheng Zhu
Google Scholar ID: WdTVEcMAAAAJ
Member of Technical Staff, OpenAI
Citations & Impact
Citations
737
H-index
9
i10-index
9
Publications
13
Co-authors
33
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple papers on LLM safety and controllable generation, copyright, and generalization. For example, 'AdvPrefix: An Objective for Nuanced LLM Jailbreaks', 'GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment', and more. Some works have also received awards, such as the Best Paper Award at the NeurIPS 2024 AdvML-Frontiers Workshop.
Research Experience
- Interned at Meta GenAI and FAIR, Adobe Research, and Bosch AI center.
Education
- Received M.E. from the Institute of Electronics, Chinese Academy of Sciences; B.S. from the University of Electronic Science and Technology of China. Was a visiting scholar at the University of Virginia, advised by Prof. David Evans. Now pursuing a Ph.D. at the University of Maryland, College Park, under the supervision of Prof. Furong Huang.
Background
- Research interests include generative artificial intelligence (such as LLM safety, reasoning, alignment, controllable generation, and agents) and trustworthy machine learning (like robustness, generalization, and equivariance). Currently a fifth-year Ph.D. candidate in the Computer Science Department at the University of Maryland, College Park.
