Paper 'Remasking Discrete Diffusion Models with Inference-Time Scaling' accepted to NeurIPS 2025; paper 'Simple Guidance Mechanisms for Discrete Diffusion Models' accepted to ICLR 2025.
Research Experience
Spent the summer of 2023 collaborating with Prof. Jian Ma at CMU.
Education
Bachelor's degree in Computer Science and Technology from Tsinghua University (2020-2024) with honor; since 2025, a Ph.D. student in Computer Science at Cornell Tech, NYC, working under Prof. Volodymyr Kuleshov.
Background
Research interests center around probabilistic generative models and their applications in scientific domains. Recently, developed a strong interest in diffusion language models.