Yuzhen Mao
yuzhenm [at] stanford [dot] edu

I am a Ph.D. student in Computer Science at Stanford University, fortunately advised by Prof. Azalia Mirhoseini and Prof. Christos Kozyrakis. My current research interests focus on efficient and agentic LLM systems, especially for long-context reasoning.

If you find any research interests that we might share, feel free to drop me an email. I am always open to potential collaborations.

Email  /  Google Scholar  /  GitHub  /  X

profile photo
News
  • [2026] Released the RSI-top blog post.
  • [2026] Released the DeLM agent plugin.
  • [2026] IceCache is accepted to ICLR 2026.
  • [2025] Started my Ph.D. at Stanford University.
Selected Publications  (* denotes equal contribution)

Decentralized Multi-Agent Systems with Shared Context
Yuzhen Mao, Jerry Gu, Aadi Chauhan, Qizheng Zhang, Hangoo Kang, Azalia Mirhoseini
arXiv preprint, 2026
Media coverage: VentureBeat

RSI-top: Escaping Exploration Collapse in Long-Horizon Autoresearch
Yuzhen Mao, Jacky Kwok, Shayan Talaei, Azalia Mirhoseini
Blog, 2026

Simplified Sparse Attention via Gist Tokens
Yuzhen Mao, Michael Y. Li, Emily B. Fox
arXiv preprint, 2026

SETA: Scaling Environments for Terminal Agents
Qijia Shen, Zhiqi Huang, Vamsidhar Kamanuru, Aznaur Aliev, Jay Rainton, Ahmed Awelkair, Zhichen Zeng, Jiajun Li, Shi Dong, Yueming Yuan, Boyuan Ma, Qizheng Zhang, Jiwei Fu, Yuzhen Mao, Wendong Fan, Ping Nie, Philip Torr, Bernard Ghanem, Changran Hu, Jonathan Lingjie Li, Urmish Thakker, Guohao Li
Conference on Neural Information Processing Systems (NeurIPS), 2026
Code  /  Dataset  /  Model

IceCache: Memory-Efficient KV-cache Management for Long-Sequence LLMs
Yuzhen Mao, Qitong Wang, Martin Ester, Ke Li
International Conference on Learning Representations (ICLR), 2026

Mem-α: Learning Memory Construction via Reinforcement Learning
Yu Wang, Ryuichi Takanobu, Zhiqi Liang, Yuzhen Mao, Yuanzhe Hu, Julian McAuley, Xiaojian Wu
arXiv preprint, 2025

IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs
Yuzhen Mao, Martin Ester, Ke Li
International Conference on Learning Representations (ICLR), 2024

Phenotype prediction from single-cell RNA-seq data using attention-based neural networks
Yuzhen Mao*, Yen-Yi Lin*, Nelson K. Y. Wong, Stanislav Volik, Funda Sar, Colin Collins, Martin Ester
Bioinformatics, 2024

Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks
Yuzhen Mao, Zhun Deng, Huaxiu Yao, Ting Ye, Kenji Kawaguchi, James Zou
ICML Workshop on Spurious Correlations, Invariance, and Stability, 2023

Augmenting Knowledge Transfer across Graphs
Yuzhen Mao, Jianhui Sun, Dawei Zhou
IEEE International Conference on Data Mining (ICDM), 2022


Design and source code from Jon Barron. Style adapted from Zhijian Liu and Ligeng Zhu.