Research Mentoring
See FAQ for more information.
See Calendar for available time slot.

Research Mentoring

Last update: 05/03/2025

We are looking for interns and visiting students at Princeton University. We welcome passionate individuals to join our research community. We believe that there will be more and more valuable research topics emerging, not fewer. We are confident that there are many paths to successful collaboration. We will do our best to find a good match and help you achieve your goals.

Currently, I am interested in several topics, including but not limited to (more details and related works here):

  • Foundations and applications of generative models, such as denoising diffusion probabilistic models (DDPMs), flow matching, and both discrete and continuous variants of diffusion models applied to text generation and scientific domains.
  • Efficient architectures for long-sequence modeling in video (both understanding and generation), language, and other modalities, using techniques such as linear attention, state space models (SSMs), RNNs, hybrid models, or sparse attention mechanisms.
  • Spatial and video understanding through efficient architectures, novel paradigm design, reinforcement learning approaches, and synthetic data generation for training.
  • Unified models for both multi-modal understanding and generation in terms of architecture design, training data, and benchmarks.
  • Benchmarking and evaluation, which must be designed to be non-trivial (State-of-the-art models achieve a accuracy of less than 20%), meaningful (in real-world applications), robust (less annotation errors), and rich in analysis (expert involved). This is, without a doubt, a highly non-trivial endeavor. My previous works often create new benchmarks and evaluation metrics along with the technical contributions.

If you are interested in more about my current and past research, please refer to this page and full publication list.

Join Discord. We are hosting Discord server among professors and students for arXiv logo daily sharing and research discussion. Welcome to join even if we don't directly work together.

I have worked—and continue to work—with many wonderful people with different backgrounds. If you would like to see my past and current students and collaborators, please refer to this page.

If you are interested in working with mes, please follow the instruction in the FAQ to schedule a meeting.

If you are also interested in working on other wonderful people in our group at Princeton University, please fill this form.