Jiamu Morris Zhang

Duncan Hall, 2090

6100 Main St

Houston, Texas 77005

About me

I’m Jiamu ‘Morris’ Zhang (张佳慕), third-year Ph.D. student in the Department of Computer Science at Rice University, where I am a member of the Chili Lab advised by Professor Hanjie Chen.

My research centers on efficient, scalable, and reliable machine learning for large language models (LLMs) and agentic systems. I’m especially drawn to system–method co-design: pairing algorithmic ideas—model compression, efficient reasoning and test-time compute control, sparsity and Mixture-of-Experts—with the systems that actually run them, from memory- and compute-aware inference to LLM serving on low-resource hardware. My goal is to make foundation models faster and cheaper without giving up quality. I’m equally interested in how we measure these systems, developing rigorous and label-efficient ways to evaluate LLM and multi-agent behavior beyond raw accuracy.

Prior to my Ph.D., I received my B.S. in the Department of Computer and Data Science from Case Western Reserve University (advisor: Shuai Xu and Vipin Chaudhary), where I worked on model compression and adversarial robustness. I was also fortunate to be mentored by Dr. Xia “Ben” Hu.

I’m really passionate about building open, efficient, and reliable AI systems. Feel free to reach out!

See my publications for a full list, or my Google Scholar profile.

news

May 01, 2026	Started as a full-time intern at Nokia AI Research & Development (Sunnyvale, CA), working on Efficiency & System–Method Co-design.

selected publications

Preprint

WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware

Jiamu Zhang, Liang Wu, Mayank Darbari, and Liangjie Hong

Preprint (work in progress), 2026

arXiv Bib

@article{zhang2026wisp,
  title = {WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware},
  author = {Zhang, Jiamu and Wu, Liang and Darbari, Mayank and Hong, Liangjie},
  journal = {Preprint (work in progress)},
  year = {2026},
}

CVPR

Flexible Group Count Enables Hassle-Free Structured Pruning

Jiamu Zhang^*, Shaochen Zhong^*, Andrew Ye, Zirui Liu, and 8 more authors

In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

Bib

@inproceedings{zhang2025flexgroup,
  title = {Flexible Group Count Enables Hassle-Free Structured Pruning},
  author = {Zhang, Jiamu and Zhong, Shaochen and Ye, Andrew and Liu, Zirui and Zhao, Sebastian and Zhou, Kaixiong and Li, Li and Choi, Soo-Hyun and Chen, Rui and Hu, Xia and Xu, Shuai and Chaudhary, Vipin},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
}

ICLR-W

Sweeping Promptable Spoofs under the DirtyRAG: A Practical, Query-Blind RAG Attack Done Right

Shaochen Zhong^*, Jiamu Zhang^*, Hoang Anh Duy Le, Wenya Xie, and 15 more authors

In ICLR 2026 Workshop on AI for Wild (AIWILD), Spotlight (under review), 2025

Bib

@inproceedings{zhang2025dirtyrag,
  title = {Sweeping Promptable Spoofs under the DirtyRAG: A Practical, Query-Blind RAG Attack Done Right},
  author = {Zhong, Shaochen and Zhang, Jiamu and Le, Hoang Anh Duy and Xie, Wenya and Lu, Yifan and Sun, Xintong and Hariri, Mohsen and Liu, Hongyi and Wang, Guanchu and Xu, Zhaozhuo and Xing, Jiarong and Liu, Zirui and Xu, Shuai and Xie, Ning and Li, Li and Chen, Rui and Tang, Ruixiang and Chaudhary, Vipin and Hu, Xia},
  booktitle = {ICLR 2026 Workshop on AI for Wild (AIWILD), Spotlight (under review)},
  year = {2025},
}

TMLR

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Yang Sui, Yu-Neng Chuang, Guanchu Wang, Jiamu Zhang, and 7 more authors

Transactions on Machine Learning Research (TMLR), 2025

arXiv Bib Code

@article{sui2025overthinking,
  title = {Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models},
  author = {Sui, Yang and Chuang, Yu-Neng and Wang, Guanchu and Zhang, Jiamu and Zhang, Tianyi and Yuan, Jiayi and Liu, Hongyi and Wen, Andrew and Zhong, Shaochen and Chen, Hanjie and Hu, Xia},
  journal = {Transactions on Machine Learning Research (TMLR)},
  year = {2025},
}