Tuo Zhang's Homepage

Publiciations

[21] Stratos: An End-to-End Distillation Pipeline for Customized LLMs under Distributed Cloud Environments
Ziming Dai*, Tuo Zhang*, Fei Gao, Xingyi Cai, Xiaofei Wang, Cheng Zhang, Wenyu Wang, Chengjie Zang (* means co-1st authors)
AAAI 2026 – Fortieth AAAI Conference on Artificial Intelligence
[Arxiv]

[20] Provenance Analysis of Archaeological Artifacts via Multimodal RAG Systems
Tuo Zhang*, Yuechun Sun*, Ruiliang Liu (* means co-1st authors)
ICCV 2025 ArtMetrics
[Arxiv]

[19] Sparkle: Optimizing the Serverless AIGC Deployment over Crowdsourced Edge Environments
Kaile Zhu, Shihao Shen, Tuo Zhang, Xiaofei Wang, Xiaoliang Wang, Xin Jiang, Wenyu Wang, Hai Jin
2nd Workshop on Networks for AI Computing (NAIC)
[Proceeding]

[18] Reconsidering LLM Uncertainty Estimation Methods in the Wild
Yavuz Bakman, Duygu Nur Yaldiz, Sungmin Kang, Tuo Zhang, Baturalp Buyukates, Salman Avestimehr, Sai Praneeth Karimireddy
ACL 2025 – The 63rd Annual Meeting of the Association for Computational Linguistics
[Arxiv] [Github] [Package Link]

[17] Leveraging Uncertainty Estimation for Efficient LLM Routing
Tuo Zhang, Asal Mehradfar, Dimitrios Dimitriadis, Salman Avestimehr
ICML 2025 Workshop on Collaborative and Federated Agentic Workflows
[Arxiv]

[16] ModalityMirror: Enhancing Audio Classification in Modality Heterogeneity Federated Learning via Multimodal Distillation
Tiantian Feng*, Tuo Zhang*, Salman Avestimehr, Shrikanth Narayanan (* means co-1st authors)
ACM NOSSDAV 25 – The 35th edition of the Workshop on Network and Operating System Support for Digital Audio and Video
[Arxiv] [Proceedings]

[15] Enabling Weak Client Participation via On-device Knowledge Distillation in Heterogenous Federated Learning
Jihyun Lim, Junhyuk Jo, Tuo Zhang, Salman Avestimehr, Sunwoo Lee
European Conference on Artificial Intelligence (ECAI) 2025
[Arxiv]

[14] FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initialization
Haonan Wang, Zeli Liu, Kajimusugura Hoshino, Tuo Zhang, John Paul Walters, Stephen Crago
ICIC 2025 – 21st International Conference on Intelligent Computing
[Arxiv]

[13] Creating a Lens of Chinese Culture: A Multimodal Dataset for Chinese Pun Rebus Art Understanding
Tuo Zhang*, Tiantian Feng*, Yibin Ni^*, Mengqin Cao*, Ruying Liu, Katharine Butler, Yanjun Weng, Mi Zhang, Shrikanth Narayanan, Salman Avestimehr (* means co-1st authors)
ACL 2025 – The 63rd Annual Meeting of the Association for Computational Linguistics
[Arxiv] [Github] [Data Website]

[12] Revisiting OPRO: The Limitations of Small-Scale LLMs as Optimizers
Tuo Zhang, Jinyue Yuan, Salman Avestimehr
ACL 2024 – The 62nd Annual Meeting of the Association for Computational Linguistics
[Arxiv]

[11] Embracing Federated Learning: Enabling Weak Client Participation via Partial Model Training
Sunwoo Lee, Tuo Zhang, Saurav Prakash, Yue Niu, Salman Avestimehr
IEEE Transactions on Mobile Computing (IEEE TMC)
[Proceeding]

[10] FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things
Samiul Alam, Tuo Zhang, Tiantian Feng, Hui Shen, Zhichao Cao, Dong Zhao, JeongGil Ko, Kiran Somasundaram, Shrikanth Narayanan, Salman Avestimehr, Mi Zhang
Journal of Data-centric Machine Learning Research (DMLR)
[Arxiv] [Github]

[9] GPT-FL: Generative Pre-trained Model-Assisted Federated Learning
Tuo Zhang^*, Tiantian Feng*, Samiul Alam, Dimitrios Dimitriadis, Mi Zhang, Shrikanth Narayanan, Salman Avestimehr (* means co-1st authors)
CVPR 2025 FedVision (Oral)
[Arxiv] [Github]

[8] FedMultimodal: A Benchmark for Multimodal Federated Learning
Tiantian Feng, Digbalay Bose, Tuo Zhang, Rajat Hebbar, Anil Ramakrishna, Rahul Gupta, Mi Zhang, Salman Avestimehr, Shrikanth Narayanan
KDD 2023 – 29^th ACM SIGKDD Conference
[Proceeding] [Arxiv] [Github]
[7] TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Training
Tuo Zhang, Lei Gao, Sunwoo Lee, Mi Zhang, Salman Avestimehr
CVPR 2023 FedVision (Oral)
[Proceeding] [Arxiv]

[6] Secure Federated Learning against Model Poisoning Attacks via Client Filtering
Duygu Nur Yaldiz^*, Tuo Zhang^*, Salman Avestimehr (* means co-1st authors)
ICLR 2023 Workshop on Backdoor Attacks and Defenses in Machine Learning (BANDS)
[Arxiv] [Github]

[5] FedAudio: A Federated Learning Benchmark for Audio Tasks
Tuo Zhang^*, Tiantian Feng*, Samiul Alam, Sunwoo Lee, Mi Zhang, Shrikanth S. Narayanan, Salman Avestimehr (* means co-1st authors)
ICASSP 2023 – 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
[Proceeding] [Arxiv] [Github]

[4] Federated Learning for Internet of Things: Applications, Challenges, and Opportunities
Tuo Zhang, Lei Gao, Chaoyang He, Mi Zhang, Bhaskar Krishnamachari, Salman Avestimehr
IEEE Internet of Things Magazine (IEEE IoTM), March 2022
[Proceeding] [Arxiv]

[3]Layer-wise Adaptive Model Aggregation for Scalable Federated Learning
Sunwoo Lee, Tuo Zhang, Salman Avestimehr
AAAI 2023 – Thirty-Seventh AAAI Conference on Artificial Intelligence
[Proceeding] [Arxiv]

[2] Federated Learning for Internet of Things: A Federated Learning Framework for On-device Anomaly Data Detection
Tuo Zhang*, Chaoyang He*, Tianhao Ma, Lei Gao, Mark Ma, Salman Avestimehr (* means co-1st authors)
ACM Embedded Networked Sensor Systems SenSys 2021 (AIChallengeIoT)
[Proceeding] [Arxiv] [GitHub]

[1] Mobility-Aware Smart Charging of Electric Bus Fleets
A Moradipari, N Tucker, T Zhang, G Cezar, M Alizadeh
2020 IEEE Power & Energy Society General Meeting (PESGM)
[Proceeding] [Arxiv]

Tuo Zhang received his Ph.D. in the Electrical Engineering department at the University of Southern California with supervision by Prof. Salman Avestimehr. Now he is an Applied Scientist in Amazon, Seattle. Before joining USC, he received his Bachelor of Science with High Honor from the University of California, Santa Barbara under the supervision of Prof. Mahnoosh Alizadeh and Prof. Forrest Brewer.

The main focus of Tuo Zhang’s research is on Privacy-Preserving Machine Learning, Edge-Cloud Infrastructure for Large Language Models, and AI for Cultural Heritage.

tuozhang [at] usc.edu