About my research interests:
I mainly work on theoretical foundations of machine learning, including online learning, optimization, and learning theory.
I'm also interested in LLM optimization, which applies modern optimization techniques (such as online sequential optimization, stochastic optimization, distributed optimization, etc) to enhance the statistical and computational efficiency of the LLM pipeline (e.g., RLHF, continuous fine-tuning, reasoning, etc).
Please refer to this page for my most recent publications.
Opportunities for undergraduate students:
If you are an NJU undergraduate student (AI, CS, math, statistics, etc), I welcome self-motivated students to join my research projects.
Please note that a successful internship or undergraduate research requires a significant commitment of your spare time to research (read literature, derive proofs, and implement code, etc). If you are passionate about research and can dedicate the necessary time, feel free to email me with your CV, transcript, a brief description of your research interests, and any other relevant materials.
I would also encourage to take my courses (Advacned Optimization and Intro to ML) for the necessary background.
您可以参考此宣讲幻灯片了解更多组内情况 [2025年本科生进组宣讲.PDF]
Prospective (master/PhD) students:
I am looking forward to self-motivated students with strong math background or programming experience. Usually, I will take about 2 students each year. If you are interested in working with me, feel free to send me an email with your CV, transcript, a description of your research interests, and other related materials. Please start your email by stating that you have read this instruction.
Other useful information:
Note for undergraduate students: I'm happy to write recommendation letters for undergraduate students applying to PhD programs at top-tier universities. For detailed and personalized letters, you should have been part of my research group for at least a year, allowing me to get to know you well. Otherwise, I can only write as a course instructor, provided you have made a strong impression in class.
Note for master/PhD students: Unfortunately, I am unable to respond to most inquiries regarding the admission possiblity for graduate students in my group. Admission is mostly handled at a department level in Nanjing University.