About Me

I am Yufei Xue. I pursue

I am currently a Ph.D. candidate at the Hong Kong University of Science and Technology supervised by Prof. Jun Zhang. I received my B.E. degree with honors from Southeast University in 2024. My research interests lie in (M)LLM Efficiency.

Download CV

Education

The Hong Kong University of Science and Technology

Ph.D. Candidate in the Department of Electronic and Computer Engineering

Supervisor: Prof. Jun Zhang

Sep. 2024 - May 2028 (Expected)

Southeast University

B.E. in Information Engineering, with Honors (Ranked 1st/246)

Sep. 2021 - May 2024

Chien-Shiung Wu College; Chien-Shiung Student (Highest Honor)

Sep. 2020 - May 2021

Experience

Tencent Hunyuan

Qingyun Intern @ AI Infra Department

Supervisor: Dr. Guanghua Yu

Apr. 2026 - Aug. 2026

Institute of Artificial Intelligence (TeleAI), China Telecom

Intern @ AI Flow Group

Supervisor: Prof. Jiawei Shao

Jun. 2025 - Mar. 2026

Peking University

Research Assistant @ Institute for Artificial Intelligence

Supervisor: Prof. Meng Li

Nov. 2023 - May 2024

Publications

  1. CoSA: Accelerating Long-Context Inference via Proxy-Kernel Co-Designed Sparse Attention
    Yufei Xue*, Lin Niu*, Hong Liu, Siran Liu, Hanyong Shao, Wei Liu, Guanghua Yu, Jianchen Zhu, Jun Zhang
    arXiv Preprint
  2. PIVOT: Efficient Query-Group Indexing for Token-Level Sparse Attention
    Hong Liu*, Yuan Cheng*, Lin Niu*, Yi Su, Yufei Xue, Anmin Liu, Guanghua Yu, Jianchen Zhu
    arXiv Preprint
  3. ProQuant: Progressive Quantization-Aware Training for Edge MLLMs
    Yufei Xue, Yushi Huang, Jiawei Shao, Pingcheng Dong, Yonghao Tan, Shiyao Li, Kwang-Ting Cheng, Xuelong Li, Jun Zhang
    Submitted
  4. VLMQ: Token Saliency-Driven Post-Training Quantization for Vision-Language Models
    Yufei Xue, Yushi Huang, Jiawei Shao, Lunjie Zhu, Chi Zhang, Xuelong Li, Jun Zhang
    arXiv Preprint
  5. Flash-VAED: Plug-and-Play VAE Decoders for Efficient Video Generation
    Lunjie Zhu, Yushi Huang, Xingtong Ge, Yufei Xue, Zhening Liu, Yumeng Zhang, Zehong Lin, Jun Zhang
    ICML 2026
  6. FLASH: An Efficient Hardware Accelerator Leveraging Approximate and Sparse FFT for Homomorphic Encryption
    Tengyu Zhang*, Yufei Xue*, Ling Liang, Zhen Gu, Yuan Wang, Runsheng Wang, Ru Huang, Meng Li
    DATE 2025

* Co-first authors

Honors & Awards

🏆
HKUST RedBird PhD Award
Aug. 2024
🎓
Merit Student of Jiangsu Province (Top 1/246)
May 2023
🏆
National Scholarship (Top 1%)
Sep. 2022
🎓
Merit Student Model (Top 1/246)
Sep. 2022
🏆
Zhishan Student Scholarship
May 2022
🎓
Annual Chien-Shiung Student (Highest Honor)
Nov. 2021
🏆
Tong-Ren-Ding Scholarship
Nov. 2021
🏆
President Scholarship (Top 2/73)
Sep. 2021
🎓
Merit Student
Sep. 2021
🏆
Zhishan Student Scholarship
May 2021