Research Mentoring
Last update: 04/17/2025
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:
- 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. My previous work including MovieChat at CVPR 2024, AuroraCap and VDC at ICLR 2025, and LongVidRWKV at CVPRW 2025.
- 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. My previous work including StableVideo at ICCV 2023, DTPM at CVPR 2024, and Science-T2I at CVPR 2025.
- Spatial and video understanding through efficient architectures, novel paradigm design, reinforcement learning approaches, and synthetic data generation for training. My previous work including STEVE at ECCV 2024, and Dynamic Token Compression at CVPR 2025.
- 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.
- Unified models for both multi-modal understanding and generation in terms of architecture design, training data, and benchmarks. My previous work including Dream Engine and An Empirical Study are also available.
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 
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.