I have joined AMD as a Senior Member of Technical Staff (Senior MTS), working on AI for hardware design. Before joining AMD, I was an Assistant Professor in the Department of Computer Science at Florida State University and a Research Scientist at Samsung Research America. My previous research explored model efficiency, post-training, and safety alignment for large language and generative models.
I received my Ph.D. in Electrical and Computer Engineering from the University of Pittsburgh in 2024, advised by Prof. Heng Huang. I earned my M.S. in Computer Systems Engineering from Northeastern University in 2017 and my B.S. in Electronic Engineering from Xidian University in 2015.
news
| Sep 24, 2026 | Two papers have been accepted as posters at NeurIPS 2026: CMPQ: Compensatory Quantization via Input-Aware Hessian Damping and PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs. |
|---|---|
| Sep 21, 2026 | I have joined AMD as a Senior Member of Technical Staff (Senior MTS), working on AI for hardware design. Many thanks to Burak Uzkent and Sharon Zhou for their help and support throughout this transition. |
| Aug 20, 2026 | Three papers have been accepted by EMNLP 2026: SALT: Salience-Aware Lexical Trie for Long-Context Compression, GeoMotionGPT: Geometry-Aligned Motion Understanding with Large Language Models, and Enabling Confidence-Aware Control of Effective Memorization in Large Language Models. |
| Apr 4, 2026 | Our paper HyperEdit: Unlocking Instruction-based Text Editing in LLMs via Hypernetworks has been accepted to Findings of ACL 2026. |
| Dec 13, 2025 | Our paper ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning was accepted by TMLR through the ICLR conference-to-journal track and presented at ICML 2026. |
| Nov 7, 2025 | Our paper Query-Efficient Domain Knowledge Stealing Against Large Language Models has been accepted as a poster at AAAI 2026. |
| Sep 19, 2025 | I have accepted the inviation to serve as an Area Chair for ICLR 2026. |
| Sep 18, 2025 | Four papers have been accepted to NeurIPS 2025: ALTER, Any Large Language Model Can Be a Reliable Judge, Cost-Aware Contrastive Routing for LLMs (Spotlight), and DictPFL. |
| Aug 20, 2025 | Our paper Controllable Memorization in LLMs via Weight Pruning has been accepted to EMNLP 2025. |
| Apr 10, 2025 | I have accepted the inviation to serve as an Area Chair for NeurIPS 2025. |
| Feb 26, 2025 | Our paper Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models has been accepted to CVPR 2025. |
| Jan 22, 2025 | Two papers have been accepted to ICLR 2025: MoDeGPT (Oral) and Not All Prompts Are Made Equal (Poster). FlexiGPT has been accepted to NAACL 2025. |
| Sep 25, 2024 | Our paper DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models has been accepted to NeurIPS 2024. |
| Sep 19, 2024 | Our paper Unlocking Memorization in Large Language Models with Dynamic Soft Prompting has been accepted to EMNLP 2024. |
| Aug 6, 2024 | I joined Florida State University as an Assistant Professor in the Department of Computer Science. |
| Mar 13, 2024 | One paper has been accepted by AAAI 2024. Four papers have been accepted by CVPR 2024. One paper has been accepted by NAACL 2024. |
| Oct 25, 2023 | One paper has been accepted by ICCV 2023. One paper has been accepted by EMNLP 2023. One paper has been accepted by WACV 2024. |
| Jan 30, 2023 | One paper has been accepted by ICLR 2023. One paper has been accepted by PAMI. |
| Nov 30, 2022 | One paper has been accepted by AAAI 2023. |
| Sep 30, 2022 | I will be a reviewer for CVPR 2023. |