Yafan Huang | University of Maryland

About Me

I am an Assistant Professor in the Department of Computer Science at the University of Maryland, College Park, with a joint appointment in UMIACS. I am broadly interested in High-Performance Computing (HPC) and AI systems, particularly from efficiency and reliability perspectives. My ultimate goal is to make computing Data-Efficient and Fault-Tolerant (DEFT).

In the past, my research has been recognized with the 2025 ACM-IEEE CS George Michael Memorial HPC Fellowship, 2026 MLCommons ML and Systems Rising Star, and nominations (or awards) for Best Paper or Best Student Paper at SC’22, SC’24, ICS’25, LDAV’25.

I am looking for self-motivated PhD students in HPC and AI systems for Fall 2027! Please check out this page for more details. If you are interested in working with me, feel free to reach out.

Already at UMD? If you are currently enrolled in UMD and interested in working with me, thank you! Please fill out this form and tell me a little about yourself and what you'd like to work on.

Selected Publications

ICS'26

Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model Inference

Yafan Huang, Sheng Di, and Guanpeng Li

[ICS'26] ACM International Conference on Supercomputing

SC'25

GPU Lossy Compression for HPC Can Be Versatile and Ultra-fast

Yafan Huang, Sheng Di, Guanpeng Li, and Franck Cappello

[SC'25] International Conference for High Performance Computing, Networking, Storage and Analysis

SC'25

lsCOMP: Efficient Light Source Compression

Yafan Huang, Sheng Di, Robert Underwood, Peco Myint, Miaoqi Chu, Guanpeng Li, Nicholas Schwarz, and Franck Cappello

[SC'25] International Conference for High Performance Computing, Networking, Storage and Analysis

SC'24

cuSZp2: A GPU Lossy Compressor with Extreme Throughput and Optimized Compression Ratio

Yafan Huang, Sheng Di, Guanpeng Li, and Franck Cappello

[SC'24] International Conference for High Performance Computing, Networking, Storage and Analysis

Best Student Paper Finalist, SC'25 Repro. Challenge Finalist

SC'24

Versatile Datapath Soft Error Detection on the Cheap for HPC Applications

Yafan Huang, Sheng Di, Zhaorui Zhang, Xiaoyi Lu, and Guanpeng Li

[SC'24] International Conference for High Performance Computing, Networking, Storage and Analysis

ISSRE'23

Characterizing Runtime Performance Variation in Error Detection by Duplicating Instructions

Yafan Huang*, Zhengyang He*, Lingda Li, and Guanpeng Li

[ISSRE'23] The 34th IEEE International Symposium on Software Reliability Engineering

SC'23

cuSZp: An Ultra-fast GPU Error-bounded Lossy Compression Framework with Optimized End-to-End Performance

Yafan Huang, Sheng Di, Xiaodong Yu, Guanpeng Li, and Franck Cappello

[SC'23] International Conference for High Performance Computing, Networking, Storage and Analysis

CCGrid'23

Towards Improving Reverse Time Migration Performance by High-speed Lossy Compression

Yafan Huang, Kai Zhao, Sheng Di, Guanpeng Li, Maxim Dmitriev, Thierry-Laurent D. Tonellot, and Franck Cappello

[CCGrid'23] IEEE/ACM International Symposium on Cluster Computing and the Grid

SC'22

Mitigating Silent Data Corruptions in HPC Applications across Multiple Program Inputs

Yafan Huang, Shengjian Guo, Sheng Di, Guanpeng Li, and Franck Cappello

[SC'22] International Conference for High Performance Computing, Networking, Storage and Analysis

Best Paper Finalist, Best Student Paper Finalist