Lu Yi (易璐)
Renmin University of China, Beijing, China
Email: yilu AT ruc.edu.cn
I am currently a 4th-year Ph.D. candidate at Gaoling School of Artificial Intelligence, Renmin University of China, where I am fortunate to be advised by Prof. Zhewei Wei. Before my graduate studies, I received my B.E. degree in Computer Science and Technology at School of Computer Science, Beijing University of Posts and Telecommunications in June 2022.
My research interests lie in LLM-based agents, with a focus on context and memory management for long-horizon tasks. Previously, my research centered on graph learning, including dynamic graph neural networks, graph unlearning, and sub-linear time algorithms for large-scale graph analysis.
News
| Sep 18, 2025 | One paper “Future Link Prediction Without Memory or Aggregation” has been accepted by NeurIPS 2025. Many thanks to my co-authors! |
|---|---|
| Feb 11, 2025 | Two papers, ScaleGUN and TGB-Seq, have been accepted by ICLR2025! ScaleGUN has been selected for a Spotlight presentation. A huge thanks to all my co-authors! You can check out the code for ScaleGUN here and the website for TGB-Seq here. |
| Apr 15, 2024 | My co-first authored paper, “Random-Walk Probability Estimation on Dynamic Weighted Graphs”, has been accepted by J-CRAD2024. Many thanks to Hanzhi! Check out the paper and code. |
| Mar 19, 2024 | One paper “A survey of dynamic graph neural networks” has been accepted by FCS2024. Many thanks to Yanping! |
| May 17, 2023 | One paper “Optimal Dynamic Subset Sampling: Theory and Applications” has been accepted by KDD2023. |
Internship
- Alibaba: Tongyi Group (Mar 2025 - Present)
- Research Intern, focusing on context management for LLM-based agents
- Mentors: Liuyi Yao, Yuexiang Xie, Yaliang Li
Selected publications
Talks
- Temporal Graph Learning Reading Group, Apr. 24, 2025, TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics. [Video] [Slide]