About me
I am a PhD student in Computer Science at UC Irvine, advised by Prof. Nalini Venkatasubramanian. I received my Master of Science in Computer Science from UC San Diego in June 2026, where I worked with Prof. Tajana Šimunić Rosing and mentor Ye Tian in SEELab on IoT and edge AI. I received my Bachelor of Engineering in Computer Science and Technology from Beihang University in June 2024.
My research focuses on distributed systems for edge LLM serving, resource-efficient inference, sensor-grounded reasoning, and privacy-aware and connectivity-resilient smart spaces. At UC Irvine, I am exploring distributed LLM serving across local edge devices and how sensing and contextual data can support locally grounded reasoning.
Education
-
University of California, Irvine — PhD student in Computer Science, September 2026–Present. Advisor: Prof. Nalini Venkatasubramanian.
-
University of California, San Diego — Master of Science in Computer Science, September 2024–June 2026. Research with Prof. Tajana Šimunić Rosing and Ye Tian in SEELab.
-
Beihang University — Bachelor of Engineering in Computer Science and Technology, September 2020–June 2024.
News
2026
- Sep
I joined UC Irvine as a PhD student in Computer Science, advised by Prof. Nalini Venkatasubramanian.
LifeAgentBench was accepted to the EMNLP main conference.
- Jun
I received my Master’s in Computer Science from UC San Diego.
- Mar
Our KLDrive preprint is available.
- Jan
Our LifeAgentBench preprint and project code are available.
2025
Our paper DailyLLM appeared at IEEE MASS 2025.
Selected Publications
LifeAgentBench: Benchmarking LLMs for Long-Horizon, Cross-Dimensional Lifestyle Health Reasoning
Ye Tian*, Zihao Wang*, Onat Gungor, Xiaoran Fan, Tajana Rosing
Conference on Empirical Methods in Natural Language Processing (EMNLP), main conference, 2026 (accepted).
*Co-first authors.
DailyLLM: Context-Aware Activity Log Generation Using Multi-Modal Sensors and LLMs
Ye Tian, Xiaoyuan Ren, Zihao Wang, Onat Gungor, Xiaofan Yu, Tajana Rosing
22nd IEEE International Conference on Mobile Ad-Hoc and Smart Systems (MASS), 2025, pp. 372–380.