Jiannan Tian joined Oakland University as a tenure-track Assistant Professor in Fall 2025, and is seeking self-motivated Ph.D. students to start their study from Spring 2026 or later. His research covers scientific computing, large-scale data reduction, data analytics, in situ neural-hybrid data reconstruction, and understanding AI, etc. He is collaborating with many researchers to innovate in building efficient HPC/AI cyberinfrastructure.
During his Ph.D. study, he worked as a student intern at Argonne National Laboratory (ANL), and published peer-reviewed work at top-tier venues. He is also the leading developer of open-source pSZ/cuSZ (link), a reference design of GPU-accelerated scientific lossy compressor.
Ph.D. positions For students interested in Ph.D. study, please reach out to jtian+phdstudy'at'oakland.edu with a brief introduction, CV, and academic transcripts.
Research Theme
Latest news
- Upcoming
We are hosting the ECHO Workshop: The 1st International Workshop on Edge-Cloud-HPC Operational Continuum, in conjunction with SC '26.
- Upcoming
We are hosting IWBDR-6: The 6th International Workshop on Big Data Reduction, with BigData '26.
-
Our team got one paper accepted at ICS '26 (1st cycle).
-
Our team got two papers accepted at IPDPS '26.
-
Our team got three papers accepted at SC '25 (acc. rate: 21.2%).
-
Our NSF CSSI project "SGCC" was awarded ($180K of $600K, PI). Many thanks to NSF!
-
Our "NeurLZ" paper was accepted at ICS '25.
-
One journal paper was accepted at CSUR.
-
Our "SZ3" paper received "the 2023 Best Paper Award" by the IEEE Computer Society Publications Board.
Selected publications
Full list on Google Scholar or in my CV (PDF).-
ICS '25NeurLZ: An online neural learning-based method to enhance scientific lossy compression The ACM International Conference on Supercomputing, Salt Lake City, June 8–11, 2025. * I co-advised in this paper.
-
SC '24cuSZ-i: High-Fidelity Error-Bounded Lossy Compression for Scientific Data on GPUs Supercomputing Conference 2024, Atlanta, GA, November 12–17, 2024. * equal contribution.
-
VLDB '24FCBench: Cross-Domain Benchmarking of Lossless Compression for Floating-point Data [Experiment, Analysis & Benchmark] 50th International Conference on Very Large Databases, Guangzhou, China (and hybrid), August 25–29, 2024.
-
TBD '23SZ3: A Modular Framework for Composing Prediction-Based Error-Bounded Lossy Compressors IEEE Transactions on Big Data.
2023 Best Paper Award, IEEE Computer Society Publications Board
-
HPDC '23Fast GPU Lossy Compressor for Scientific Computing Applications The ACM International Symposium on High-Performance Parallel and Distributed Computing (in conjunction with the Federated Computing Research Conference), Orlando, Florida, June 20–23, 2023. * equal contribution.
-
CLUSTER '21Optimizing Error-Bounded Lossy Compression for Scientific Data on GPUs Proceedings of the 2021 IEEE International Conference on Cluster Computing, (Virtual Event) Portland, OR, September 7–10, 2021.
-
IPDPS '21 Huffman Coding: Toward Extreme Performance on Modern GPU Architectures IEEE International Parallel & Distributed Processing Symposium, (Virtual Event) Portland, OR, May 17–21, 2021.
-
PACT '20cuSZ: A High-Performance GPU Based Lossy Compression Framework for Scientific Data The 29th International Conference on Parallel Architectures and Compilation Techniques, (Virtual Event) Atlanta, GA, October 3–7, 2020.
-
PPoPP '20waveSZ: A Hardware-Algorithm Co-Design of Efficient Lossy Compression for Scientific Data Proceedings of the 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, San Diego, CA, February 22–26, 2020.