About Me
I received my Ph.D. in Electrical and Computer Engineering from the State University of New York at Binghamton in 2023. Prior to that, I earned an M.S. (2019) and a B.S. (2016) in Statistics from Nankai University (China). In 2024, I served as a postdoctoral scholar at the University of California, Merced, where I further advanced my research expertise.
Research Interests
My research centers on high-performance network optimization, cloud and edge computing, distributed machine learning, and federated learning. A key focus is addressing security challenges in distributed systems, with an emphasis on designing robust attack mitigation and defense strategies. I strive to advance the efficiency, scalability, and resilience of modern computing infrastructures through innovative and interdisciplinary approaches.
Join NODI Lab.
NODI Lab. is seeking three Ph.D. students to start in Fall 2026. Applicants should hold or expect to complete a degree in Computer Science, Electrical Engineering, Statistics, or a related field. Strong programming skills and a solid mathematical background are required. To apply, please email your CV, transcripts, and a brief research statement to gyan8@jlu.edu.cn. We also invite applications for postdoc researchers and tenure-track faculty positions. Candidates must hold a Ph.D. in a relevant area.
For more information about our lab, visit NODI Lab.’s homepage.
Recent News
[January 2026] [Paper] Our paper "MaRS: Memory-Adaptive Routing for Reliable Capacity Expansion and Knowledge Retention" accepted to ICLR 2026.
[October 2025] [Paper] Our paper "Joint tensor ring decomposition and unidirectional total variation for seismic data denoising" accepted to IEEE Trans. TGRS.
[Septermber 2025] [Paper] Our paper "FedRACE: A Hierarchical and Statistical Framework for Robust Federated Learning" accepted to NeurIPS 2025.
[Septermber 2025] [Paper] Our paper "KaRF: Weakly-Supervised Kolmogorov-Arnold Networks-based Radiance Fields for Local Color Editing" accepted to NeurIPS 2025.
[August 2025] [Paper] Our paper "FedSTEP: Asynchronous and Staleness-Aware Personalization for Efficient Federated Learning" accepted to CIKM 2025.
[May 2025] [Paper] Our paper "FedDiAL: Adaptive Federated Learning with Hierarchical Discriminative Network for Large Pre-trained Models" accepted to ACM KDD 2025.