Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
Published multiple high-impact papers, including 'Pre³: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation' (2025), 'Past-Future Scheduler for LLM Serving under SLA Guarantees' (2025), 'Pushing the Limit of Post-Training Quantization' (2025), etc.
Winner of IEEE Low Power Computer Vision Challenge (2023)
Recipient of 2023 IEEE UAV Chase Challenge Award
Winner of IEEE Low Power Computer Vision Challenge (2021)
Selected for Tencent Rhino-Bird Elite Training Program (2020)
Named SenseTime Future Star Talent (2019)
Awarded National Scholarship by Ministry of Education (2019)
Received CCF Outstanding Undergraduate Award (2018)
Research Experience
Developed LightX2V: Light Video Generation Inference Framework
Led LLMC: An off-the-shelf tool for compressing large language models using state-of-the-art compression algorithms
Developed LightLLM: A lightweight, scalable, and high-performance Python-based LLM inference and serving framework
Implemented the winning solution for LPCV 2023 Challenge
Implemented the winning solution for LPCV 2021 FPGA Track
Developed MQBench: An open-source PyTorch FX-based model quantization toolkit