Efficient & controllable safety alignment
Safety recovery after fine-tuning and modular adaptation for domain-specific control of model behavior.
Ph.D. Student in Computer Science
I am a Ph.D. student at the University of Georgia, advised by Prof. Geng Yuan. I earned my bachelor’s degree at Central China Normal University in 2024.
My research focuses on efficient and trustworthy foundation models, spanning optimization, model compression, hardware-aware deployment, and safety alignment.
Safety recovery after fine-tuning and modular adaptation for domain-specific control of model behavior.
Low-bit quantization and hardware-friendly training for models operating under memory and compute constraints.
Layer-wise optimization, informative negative sampling, and token pruning for more effective learning.
Two papers were accepted to NeurIPS 2026.
Three papers were accepted to EMNLP 2026.
Joined Amazon as an Applied Scientist Intern in Seattle, working on LLM inference reliability.
Honored to receive the 2026 James L. Carmon Scholarship Award.
One paper was accepted to NeurIPS 2025.
One paper was accepted to ICCAD 2025 and received a Best Paper Nomination.
One paper was accepted to ICLR 2025.
Joined UGA to begin my Ph.D. in Computer Science.
* Equal contribution.
Advances in Neural Information Processing Systems (NeurIPS), 2026
Advances in Neural Information Processing Systems (NeurIPS), 2026
Findings of Empirical Methods in Natural Language Processing (EMNLP Findings), 2026
Findings of Empirical Methods in Natural Language Processing (EMNLP Findings), 2026
Advances in Neural Information Processing Systems (NeurIPS), 2025
IEEE/ACM International Conference on Computer-Aided Design (ICCAD), 2025Best Paper Nomination
The Thirteenth International Conference on Learning Representations (ICLR), 2025
Machine Learning (MLJ), 2023
No publications in this category.
Applied Scientist Intern · Seattle, WA
Ph.D. Student in Computer Science
School of Computing
Advisor: Prof. Geng Yuan
Bachelor’s Degree in Information Science
School of Information Management
Advisors: Prof. Guanghui Ye and Prof. Chuan Wu