About Me
I am a Ph.D. candidate in the School of Computer Science at Nanjing University. My research focuses on building efficient systems for Large Language Models.
Education
Nanjing University
2025.09 – PresentPh.D. in Computer Science
School of Computer Science
Advised by Prof. Chen Tian and Prof. Zhibin Wang
Harbin Institute of Technology
2021.09 – 2025.06B.S. in Computer Science
School of Future Technology
Experience
Alibaba Tongyi Lab
2026.01 – PresentResearch Intern
LLM Inference Optimization, Scheduling Optimization
Alibaba Cloud
2024.11 – 2025.04Research Intern
Network Innovation Engineering, Multi-Agent Diagnosis
Research
Speculative Decoding for LLMs
Developing novel approaches to accelerate large language model inference through speculative decoding. By leveraging diffusion-inspired methods, we can generate multiple tokens simultaneously while maintaining output quality, achieving significant speedups in real-world serving scenarios.
LLM Serving Systems
Building efficient systems for serving large language models at scale, focusing on optimizing throughput and latency through system-level innovations in scheduling, memory management, and parallelism strategies.