Boyuan Zhang (张博源)

About

I am an Assistant Professor in the Department of Computer Science at the University of Kentucky, where I joined in August 2026, and director of the THREAD Lab.

My research focuses on high-performance computing (HPC), GPU-accelerated data compression, machine learning systems, and quantum computing. I develop efficient parallel algorithms and systems that reduce memory usage and data movement in scientific and AI workloads. My work includes lossy and lossless compression on GPUs, compression for large language model inference and distributed training, and scalable quantum circuit simulation. Across these areas, I aim to improve performance and scalability while preserving the fidelity of scientific results.

I received my Ph.D. in Intelligent Systems Engineering from Indiana University Bloomington in June 2026, advised by Prof. Fengguang Song and Prof. Dingwen Tao. Before that, I earned my M.S. in Electrical Engineering from the University of Southern California in 2020 and my B.Eng. in Information Engineering from Shanghai Jiao Tong University in 2018.

I have collaborated with Pacific Northwest National Laboratory, Argonne National Laboratory, and Meta. I was a Research Intern at Pacific Northwest National Laboratory in summer 2023 and a Research Scientist Intern at ByteDance in summer 2025. My work received the Best Paper Runner-Up award for BMQSim and a Best Paper Candidate nomination for Aatrox at ACM ICS'25. See my publications and curriculum vitae (PDF) for more details.

Openings

THREAD Lab is recruiting fully funded Ph.D. students beginning Fall 2026. Students interested in HPC and data-intensive computing are encouraged to apply. View opening details.

News

2026
Serving on the program committee of PPoPP'27.
2026
Serving on the program committee of IPDPS'27.
2026
Serving as Publicity Chair for NPC'27.
2026
Serving as Web & Publicity Chair for SSDBM'27.
2026
One paper accepted at ICS'26.
2026.08
Xizhi Zhan joined THREAD Lab.
2026.08
Joined the University of Kentucky as an Assistant Professor.
2026.03
Two papers accepted at IPDPS'26.
2025.11
Served as a student volunteer at SC'25.
2025.06
Awarded Best Paper Runner-Up at ACM ICS'25 for BMQSim.
2025.06
Nominated as Best Paper Candidate at ACM ICS'25 for Aatrox.
2025.06
One paper accepted at SC'25.
2025.05
Joined ByteDance (Seed, ML Systems) as a research intern, working on LLM inference optimization.
2025.03
Three papers accepted at ICS'25.
2024.10
One paper and one poster accepted at PPoPP'25.
2024.07
Two papers accepted at SC'24.
2024.02
One paper accepted at DAC'24.
2023.11
Served as a student volunteer at SC'23.
2023.05
Joined Pacific Northwest National Laboratory as a research intern.
2023.04
One paper accepted at HPDC'23.
2023.04
One paper accepted at ICS'23.
2022.08
Started research collaboration with Meta on compression for distributed training.

Selected Publications

IPDPS'26

Near-Zero Cost KV Cache Compression for Large Language Model Inference

Boyuan Zhang, Ding Zhou, Yafan Huang, Shihui Song, Hao Feng, Jinda Jia, Chengming Zhang, and Zhi Zhang.

Proceedings of the 40th IEEE International Parallel and Distributed Processing Symposium, 2026.

IPDPS'26

Accelerating AI Compression through Lightweight Lossless Encoding and Pipelined Workflows

Boyuan Zhang, Luanzheng Guo, Jiannan Tian, Jinyang Liu, Daoce Wang, Chengming Zhang, Bo Fang, Fengguang Song, Jan Strube, Nathan R. Tallent, and Dingwen Tao.

Proceedings of the 40th IEEE International Parallel and Distributed Processing Symposium, 2026.

ICS'25Best Paper Runner-Up

BMQSim: Overcoming Memory Constraints in Quantum Circuit Simulation with a High-Fidelity Compression Framework

Boyuan Zhang, Bo Fang, Fanjiang Ye, Luanzheng Guo, Fengguang Song, Nathan R. Tallent, and Dingwen Tao.

Proceedings of the 39th ACM International Conference on Supercomputing, pp. 689–704, 2025.

ICS'25Best Paper Candidate

Pushing the Limits of GPU Lossy Compression: A Hierarchical Delta Approach

Boyuan Zhang, Yafan Huang, Sheng Di, Fengguang Song, Guanpeng Li, and Franck Cappello.

Proceedings of the 39th ACM International Conference on Supercomputing, pp. 654–669, 2025.

SC'24

Accelerating Communication in Deep Learning Recommendation Model Training with Dual-Level Adaptive Lossy Compression

Hao Feng*, Boyuan Zhang*, Fanjiang Ye, Min Si, Ching-Hsiang Chu, Jiannan Tian, Chunxing Yin, Summer Deng, Yuchen Hao, Pavan Balaji, Tong Geng, and Dingwen Tao.

SC24: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1–16, IEEE, 2024.

HPDC'23

FZ-GPU: A Fast and High-Ratio Lossy Compressor for Scientific Computing Applications on GPUs

Boyuan Zhang, Jiannan Tian, Sheng Di, Xiaodong Yu, Yunhe Feng, Xin Liang, Dingwen Tao, and Franck Cappello.

Proceedings of the 32nd International Symposium on High-Performance Parallel and Distributed Computing, pp. 129–142, 2023.

ICS'23

GPULZ: Optimizing LZSS Lossless Compression for Multi-Byte Data on Modern GPUs

Boyuan Zhang, Jiannan Tian, Sheng Di, Xiaodong Yu, Martin Swany, Dingwen Tao, and Franck Cappello.

Proceedings of the 37th ACM International Conference on Supercomputing, pp. 348–359, 2023.

* denotes equal contribution. See the complete publication list.