Hi there! I’m Qi Li, a CS PhD student at Tsinghua University, where I also serve as a visiting student at HKUST-GZ. I received my Master’s degree in Engineering from Tsinghua University, and my Bachelor’s degree in Engineering from Lanzhou University (LZU).

My current research interests focus on:

Efficient algorithm for LLM: PEFT, Knowledge Editing
Post-training of LLM
Machine learning systems for LLM
Understanding LLM from both theoretical and empirical perspectives

I’m open to collaboration and discussion. Feel free to reach out via email!

Email: lqinfdim AT 163.com

🔥 News

2026.01: 🎉🎉 One paper is accepted by ICLR 2026.
2025.09: 🎉🎉 One paper is accepted by NeurIPS 2025.
2025.05: 🎉🎉 One paper is accepted by ACL 2025.
2025.04: 🎉🎉 One paper is accepted by ISIT 2025.
2024.09: 🎉🎉 One paper is accepted by NeurIPS 2024.
2024.05: 🎉🎉 One paper is accepted by ACL 2024.

📖 Educations

2025.08 - Current, Tsinghua University, PhD Student.
2019.08 - 2022.08, Tsinghua University, Master of Engineering.
2014.09 - 2018.06, Lanzhou University, Bachelor of Engineering.

📝 Selected Publications

Li Q, Wu J, Liu X, et al. Reasoning language model inference serving unveiled: An empirical study[J]. Long Paper of The Fourteenth International Conference on Learning Representations (ICLR 2026, Tsinghua-A).
Li Q. et.al. AdaEdit: Advancing Continuous Knowledge Editing For Large Language Models. Long paper of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025, CCF-A).
Qingyue Zhang, Haohao Fu, Guanbo Huang, Yaoyuan Liang, Chang Chu, Tianren Peng, Yanru Wu, Qi Li, Yang Li, Shao-Lun Huang. A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning. Main Track Paper of the Thirty-nith Annual Conference on Neural Information Processing Systems (NeurIPS 2025, CCF-A).
T. Peng, Q. Li, S.-L. Huang, “On the Optimal Second-Order Convergence Rate of Minimax Estimation Under Weighted MSE,” IEEE International Symposium on Information Theory, Jun., 2025. (ISIT 2025 Oral, Tsinghua B)
Li Q. et.al. Should We Really Edit Language Models? On the Comprehensive Evaluation of Edited Language Models. Main Track Paper of the Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024, CCF-A).
Li, Q. et al. Can We Continually Edit Language Models? On the Knowledge Attenuation in Sequential Model Editing. Long paper of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024, CCF-A).
Li, Q. et.al. Harnessing the Power of Pre-trained Vision-Language Models for Efficient Medical Report Generation. Long Paper of 32nd ACM International Conference on Information and Knowledge Management (CIKM 2023 Oral, CCF-B).

💻 Projects

(For more details can click the images)

🎖 Honors and Awards

2015.12, First Class Scholarship for Outstanding Students, Lanzhou University.
2017.12, First Class Scholarship for Outstanding Students, Lanzhou University.
2015.12, Outstanding Student at Lanzhou University.
2016.12, Outstanding Student at Lanzhou University.
2017.12, Outstanding Student at Lanzhou University.
2020.12, Scholarship for Excellent Students, Tsinghua Shenzhen International Graduate School.

👔 Academic Services