About me

I am a fourth-year Ph.D. student in Electrical and Computer Engineering at the University of Maryland, College Park, advised by Prof. Ang Li in the CASE Lab. My research lies at the intersection of machine learning and systems.

I have worked as a Research Intern at Meta (Summer 2026) and Snowflake (Summer 2025), and as a Research & Development Engineer at Tencent (2021–2023).

CV · Email · Google Scholar · GitHub · LinkedIn

Research Interests

I work on making machine learning models efficient to train, adapt, and deploy, with a focus on:

Efficient LLM systems: training and serving, KV-cache compaction, and model efficiency.
Edge AI: on-device inference and heterogeneous mobile computing.
Model adaptation and distributed learning: parameter-efficient fine-tuning and federated learning.

Selected Publications

View all publications · * Equal contribution

2026

Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL.
Z. Yao, G. Sun, Ł. Borchmann, Zheyu Shen, M. Deng, B. Zhai, H. Zhang, A. Li, Y. He.
ACL Findings 2026
Uncovering the Redundancy in Transformers via a Unified Study of Layer Dropping.
S. He, G. Sun, Zheyu Shen, A. Li.
Transactions on Machine Learning Research (TMLR), 2026
HeteroVDiff: Pipelining Video Diffusion across Mobile NPU and GPU with Shared Weights.
Zheyu Shen, Z. Wang, Y. He, G. Sun, Y. Zhang, Y. Wang, W. Ye, A. Li.
arXiv preprint arXiv:2610.16244 (2026)
ARC-KV: Amortizing Anchor Search for Reconstruction-Based KV Cache Compaction.
Zheyu Shen, G. Wang, D. Tu, M. Zhang, Y. Li, A. Aziz, C. Tang, A. Li.
arXiv preprint arXiv:2609.36835 (2026)

2025

Bag of Tricks for Sparse Mixture-of-Experts: A Benchmark Across Reasoning, Efficiency, and Safety.
M. Qiu^*, Zheyu Shen^*, P. Li, A. Li, T. Chen.
EMNLP Findings 2025
EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices.
Zheyu Shen, Y. He, Z. Wang, Y. Zhang, G. Sun, W. Ye, A. Li.
MobiSys 2025
Prada: Black-Box LLM Adaptation with Private Data on Resource-Constrained Devices.
Z. Wang, Y. He, Zheyu Shen, Y. Li, G. Sun, M. Lee, A. Li.
arXiv preprint arXiv:2503.14932 (2025)

2024

Flora: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations.
Z. Wang, Zheyu Shen, Y. He, G. Sun, H. Wang, L. Lyu, A. Li.
NeurIPS 2024
Domino: Eliminating Communication in LLM Training via Generic Tensor Slicing and Overlapping.
G. Wang, C. Zhang, Zheyu Shen, A. Li, O. Ruwase.
arXiv preprint arXiv:2409.15241 (2024)

Education

University of Maryland, College Park · 2023–present
Ph.D. in Electrical and Computer Engineering, A. James Clark School of Engineering.
University of Southern California · 2019–2020
M.S. in Computer Science, Viterbi School of Engineering.
Northwestern Polytechnical University · 2014–2018
B.S. in Software Engineering, School of Software.

Professional Experience

Meta — Research Intern · Summer 2026
Developed ARC-KV, a KV-cache compaction algorithm that compresses long-context KV caches in seconds while maintaining high accuracy.
Snowflake — Research Intern · Summer 2025
Developed Arctic-Text2SQL-R1 (ACL Findings 2026), improving reinforcement-learning training throughput for Text-to-SQL.
Tencent — Research & Development Engineer · 2021–2023
Built a TensorFlow-based online training system for sparse models and a distributed inference system serving trillion-parameter models via a parameter server.

Honors & Awards

Graduate School Dean’s Fellowship, 2023.

Academic Service

Reviewer: ICLR and NeurIPS.

Zheyu Shen