Computer Science · NYU Courant
I'm currently a first-year CS PhD student at NYU Courant, advised by Saining Xie. I obtained my bachelor degree at Shanghai Jiao Tong University, ACM Honor Class.
My research aims to understand the dynamics of high-dimensional, continuous, and often noisy data spaces. Representations, as a special form of data generated by neural networks, are particularly interesting to me. I'm specifically attracted to how to make predictions (of various types) on these representations and to model them efficiently. Concretely, I mainly work on (visual) representation learning, generative models, and multimodal learning. I also have some experience in low-level vision and adversarial examples.
Internship begins! I'm now a summer intern at AMI Labs.
New blog post (with Peter Tong): Lessons from Two Years of TPU Training in Academia — sharing hard-earned TPU debugging wisdom!
Enrolled as a PhD student at NYU Courant, advised by Saining Xie.
Graduated from Shanghai Jiao Tong University with an Honor degree in Computer Science, ACM Honor Class.
Internship begins! I'm now an intern at NYU VisionX Lab, advised by Saining Xie, doing research on generative models and MLLMs. I'll be on site at July, see you in New York!
Internship begins! I'm now an intern at Shanghai AI Lab, advised by Chao Dong, doing research on MLLM and their possible applications on low-level vision tasks.
Research
arXiv 2026
A systematic study of unified multimodal pretraining with representation autoencoders and Mixture-of-Experts, showing how visual data complements language, enables world modeling, and benefits both understanding and generation.
ICLR 2026
A class of autoencoders that utilize pretrained, frozen representation encoders as encoders and train ViT decoders on top. Training Diffusion Transformers in the latent space of RAE achieves strong performance and fast convergence on image generation tasks.
arXiv 2024
A careful designed framework to let a frozen LLM to perform low-level vision tasks without any multi-modal data or prior. We also find that most current MLLMs(2024.5) with generation ability are BLIND to low-level features.
ICLR 2025spotlight
A method to craft adversarial examples for Latent Diffusion Model against various personlization techniques(e.g. SDEdit, LoRA), strongly outperforming existing methods. We aim for protecting the privacy of artists and their copyrighted works in the era of AIGC.
NY Milk Tea Board A personal ranking of milk tea and bottled tea around New York.
