Bio
My name is Yun (Catherine) Cheng. I am a second-year CS Ph.D. student at Princeton University, advised by Sanjeev Arora. I completed my M.S. in Machine Learning, B.S. in Computer Science, and B.S. in Mathematical Sciences from Carnegie Mellon University.
My research focuses on conceptual understanding of large language models and vision-language models, with broad interests in developing better, self-evolving AI
Updates
[05/2025] | Our paper Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? was accepted by ICML 2025! |
[01/2024] | Our paper Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications was accepted by ICLR 2024! |
[09/2023] | Our paper Quantifying & modeling multimodal interactions: An information decomposition framework was accepted by NeurIPS 2023! |