🏫 I’m a senior student at Zhejiang University, majoring in Computer Science and Technology.
🔭 I’m interested in Efficient AI through algorithm–system co-design, focusing on hardware-friendly sparse and quantized module design as well as efficient inference strategies.
🚀 I’m currently a leader of ZJUSCT, a super computing team at Zhejiang University which has won several international super computing competitions.
News
📢 New Preprint: TriAttention
2026-04-07Excited to share our latest preprint on TriAttention, an efficient KV cache compression method for long reasoning in large language models. By leveraging Q/K concentration in pre-RoPE space and a trigonometric series to score key importance, TriAttention matches Full Attention reasoning accuracy on AIME25 while achieving 2.5x higher throughput or 10.7x KV memory reduction. Check out the project page and code!
📢 New Preprint: Pyramid Sparse Attention (PSA)
2025-12-03Excited to share our latest preprint on Pyramid Sparse Attention (PSA), a novel attention mechanism designed to enhance efficiency in video understanding and generation tasks. PSA leverages a multi-level sparse attention strategy to allocate computational resources effectively, enabling the model to focus on critical tokens while reducing redundancy. Check out the paper on project page!
Publications
A collection of my research publications and academic papers.
Experience
Team Leader
Led a team of students in participating in various supercomputing competitions, focusing on machine learning systems (MLSys) and high-performance computing (HPC) solutions.
Teaching Assistant
Assisted in the HPC101 course, focusing on high-performance computing concepts and practical applications.
- Contributed to experiment design and implementation about deep learning.
- Given a lecture on deep learning system.
- Collaborated with other TAs in scheduling the course, refining course materials and providing support to students.
Member
Contributed to the development of HPC solutions and participated in various supercomputing competitions both domestically and internationally.
Teaching Assistant
Assisted Prof. Chang in teaching the Computer Architecture course.
- Provided support in grading assignments and exams.
- Refined course and experiment materials.
- Examined students’ works in experiments and provided feedback.
Teaching Assistant
Assisted in the HPC101 course, focusing on high-performance computing concepts and practical applications.
- Contributed to experiment design and implementation about MPI/OpenMP.
- Given a lecture on MPI and OpenMP parallel programming models, with co-lecturer Chenxiao Li and Jiarui Guo.
Awards
National Scholarship of China
Recipient
ASC25 Student Supercomputer Challenge
First Prize
ASC25 Student Supercomputer Challenge
Application Innovation Award
5th Linear Solver Algorithm and Performance Optimization Competition
Third Prize
Zhejiang University Scholarship
First Prize
4th Linear Solver Algorithm and Performance Optimization Competition
Second Prize
ISC 2024 Student Cluster Competition (online)
4th Place
ASC24 Student Supercomputer Challenge
Second Prize
Zhejiang University Scholarship
Third Prize
Education
Blog
Visit my personal blog to read about my thoughts, experiences, and technical insights.