Kun Li is an Assistant Researcher / Assistant Professor at the Institute for AI Industry Research (AIR), Tsinghua University. His research focuses on the intersection of high-performance computing (HPC) and artificial intelligence (AI) in scientific and engineering applications. His research interests include Physical AI, AI for Science, and Efficient AI systems.
His research has been published in top-tier international systems conferences and journals, including SC, PPoPP, ASPLOS, USENIX ATC, ICS, TACO, and TPDS. He designed and developed OpenKMC, an indigenously developed nuclear materials simulation software, achieving large-scale irradiation damage evolution simulations with over 100 billion atoms on 5 million CPU cores on the Sunway supercomputing platform. He also proposed the MatrixScience computing paradigm and built Mako, a highly scalable quantum chemistry computing system targeting cloud platforms and AI accelerators.
His work has received the PPoPP 2024 Best Paper Award (sole recipient), SC 2025 Best Student Paper Award Finalist, and SC 2025 Reproducibility Challenge Finalist. He has also received the CCF Outstanding Ph.D. Dissertation Award, CCF HPC Young Scientist Award, ACM SIGHPC China Rising Star Award, and ACM SIGHPC China Outstanding Ph.D. Dissertation Award. He was invited to deliver keynote talks at HPC China 2024 and ChinaSC 2025, and has served multiple times as a Program Committee member for leading international conferences such as SC, PPoPP, and ISC.
Contact
Email: likun@air.tsinghua.edu.cn
Homepage: https://www.likun.tech/
Professional Experience
Dec 2025 – Present
Assistant Researcher / Assistant Professor,
Institute for AI Industry Research (AIR), Tsinghua University
Jul 2022 – Dec 2025
Senior Researcher, Microsoft Research Asia
Selected Publications
ConvStencil: Transforming Stencil Computation to Matrix Multiplication on Tensor Cores.
Yuetao Chen, Kun Li*, Yuhao Wang, Donglin Bai, Lei Wang, Lingxiao Ma, Liang Yuan, Yunquan Zhang, Ting Cao, Mao Yang.
PPoPP 2024.
SparStencil: Retargeting Sparse Tensor Cores to Scientific Stencil Computations via Structured Sparsity Transformation.
Qi Li, Kun Li*, Haozhi Han, Liang Yuan, Yunquan Zhang, Yifeng Chen, Junshi Chen, Hong An, Ting Cao, Mao Yang.
SC 2025.
LoRAStencil: Low-Rank Adaptation of Stencil Computation on Tensor Cores.
Yiwei Zhang, Kun Li*, Liang Yuan, Jiawen Cheng, Yunquan Zhang, Ting Cao, Mao Yang.
SC 2024.
Matrix Is All You Need: Rearchitecting Quantum Chemistry to Scale on AI Accelerators.
Haozhi Han, Kun Li*, Fusong Ju, Qi Li, Yifeng Chen, Yunquan Zhang, Ting Cao, Mao Yang.
SC 2025.
LONG EXPOSURE: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity.
Tuowei Wang, Kun Li*, Zixu Hao, Donglin Bai, Ju Ren, Yaoxue Zhang, Ting Cao, Mao Yang.
SC 2024.
