Ziyao Wang (王子瑶)
I’m currently a third-year Ph.D. student in the Department of Electrical and Computer Engineering at the University of Maryland, College Park, advised by Prof. Ang Li. Before that, I received my B.E. in Computer Engineering from Wuhan University, where I was fortunate to work with Prof. Qian Wang. I worked as a research intern at IBM Research (2024 summer) and Sony AI (2025 summer) on the topic of collaborative and efficient foundation models.
I prefer simple, elegant approaches to improving the performance and efficiency of foundation models. I focus on developing advanced collaborative edge AI systems, with three priorities: performance, efficiency, and security.
Selected Publications
(* = equal contribution)
Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding
Ziyao Wang, Muneeza Azmat, Ang Li, Raya Horesh, Mikhail Yurochkin.
ICML 2025
FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations
Ziyao Wang, Zheyu Shen, Yexiao He, Guoheng Sun, Hongyi Wang, Lingjuan Lyu, Ang Li.
NeurIPS 2024
FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent
Ziyao Wang, Jianyu Wang, Ang Li.
ICLR 2024
UPTON: Unattributable Authorship Text via Data Poisoning
Ziyao Wang, Dongwon Lee, Thai Le.
EMNLP 2023
Prada: Black-Box LLM Adaptation with Private Data on Resource-Constrained Devices
Ziyao Wang, Yexiao He, Zheyu Shen, Yu Li, Guoheng Sun, Myungjin Lee, Ang Li.
arXiv: 2503.14932
One Communication Round is All It Needs for Federated Fine-Tuning Foundation Models
Ziyao Wang, Bowei Tian, Yexiao He, Zheyu Shen, Luyang Liu, Ang Li.
arXiv: 2412.04650
Predictive Auditing of Hidden Tokens in LLM APIs via Reasoning Length Estimation
Ziyao Wang*, Guoheng Sun*, Yexiao He, Zheyu Shen, Bowei Tian, Ang Li.
arXiv: 2508.00912
Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM Services
Guoheng Sun*, Ziyao Wang*, Xuandong Zhao, Bowei Tian, Zheyu Shen, Yexiao He, Jinming Xing, Ang Li.
arXiv: 2505.18471
A GAN-based Defense Framework against Model Inversion Attacks
Xueluan Gong*, Ziyao Wang*, Yanjiao Chen, Qian Wang.
TIFS
Kaleidoscope: Triggering Backdoor with RGB Filters
Xueluan Gong*, Ziyao Wang*, Yuzhe Gu, Yanjiao Chen, Qian Wang.
TDSC