- Many-to-many Image Generation with Auto-regressive Diffusion Models
- InternalInspector I2: Robust Confidence Estimation in LLMs through Internal States
- Recipient of the Amazon-VT Fellowship for the 2023-2024 academic year
Research Experience
- Machine Learning Research Intern, Apple, May 2025 – Sep 2025, Cupertino, CA
- Machine Learning Research Intern, Apple, May 2023 – Aug 2023, New York, NY
- Research Associate, Language Technologies Institute, Carnegie Mellon University, Jan 2019 – Dec 2019, Pittsburgh, PA
- Graduate Research Assistant, MultiComp Laboratory, Carnegie Mellon University, worked with Prof. Louis-Philippe Morency and Prof. Graham Neubig
Education
- Ph.D. in Computer Science, Present, University of Illinois Urbana-Champaign
- Ph.D. in Computer Science, 2024, Virginia Tech, advised by Prof. Lifu Huang and Prof. Ismini Lourentzou
- MSc in Intelligent Information Systems, 2018, Carnegie Mellon University
- BEng in Software Engineering, 2017, School of Software Engineering, Fudan University
Background
Research Interests: Multimodal Interaction, Deep Learning, Multimodal Machine Learning, Deep Generative Models, Natural Language Processing, Computer Vision. Summary: Focused on developing efficient, controllable, adaptive, and interactive multimodal generative models to build robust AI agents capable of understanding, interpreting, and reasoning about the physical world.