About Me

I am a first-year PhD student in Yale University, advised by Prof. Zhong Lin. Before joining Yale, I was a Master student at Tsinghua University, advised by Prof. Yangdong Deng.

Efficiency lies at the heart of computer science. My current focus is on Efficient AI System, where I am deeply committed to exploring approaches that bridge algorithmic advancements and system-level optimizations. Most recently, I have been working on AI memory systems, which I believe are key to advancing toward AGI.

Outside of research, I enjoy running, swimming and books on history and sociology.

Email  /  Google Scholar  /  Github  /  Zhihu

profile photo
🎓 Education
  • Yale University, PhD Student, Computer Science, 2025.09 - Present
  • Tsinghua University, M.S., Software Engineering, 2022.09 - 2025.06
  • Wuhan University, B.S., Computer Science, 2018.09 - 2022.06
🔥 News
  • [Jul. 2025] Arrived at Yale!
  • [Nov. 2024] Received PetroChina Scholarship at Tsinghua University!
  • [May. 2024] CQIL is accepted to ACL 2024!
  • [May. 2024] Ended my journey in Vienna for ICLR 2024 and enriched my mind with those remarkable papers!
  • [Jan. 2024] First Paper accepted to ICLR 2024!
  • [Aug. 2022] Arrived Tsinghua University and started my journey in Beijing.
📑 Publications
KVBuffer: IO-aware Serving for Linear Attention
Longwei Zou, Lin Zhong
Preprint, 2026
arXiv

InstCache: A Predictive Cache for LLM Serving
Longwei Zou, Tingfeng Liu Kai Chen Jiangang Kong Yangdong Deng
Preprint, 2025
arXiv

CQIL: Inference Latency Optimization with Concurrent Computation of Quasi-Independent Layers
Longwei Zou, Qingyang Wang Han Zhao Jiangang Kong Yi Yang Yangdong Deng
ACL, 2024
github / arXiv

A Multi-Level Framework for Accelerating Training Transformer Models
Longwei Zou, Han Zhang Yangdong Deng
ICLR, 2024
github / arXiv


Design and source code from Jon Barron's website.