I am an undergraduate researcher focusing on Machine Learning, Representation Learning, and Optimization Theory. Rather than simply utilizing state-of-the-art applications, I pursue the underlying mathematical rigor of linear algebra and optimization theory to deeply understand how complex neural architectures learn and converge. This foundational focus drives my core research interest: exploring the Training Dynamics and implicit biases of generative models.

Recently, I have extended my research interests to Cognitive Science and Neuroscience. This expansion stems from a desire to bridge the fundamental gap between compute-intensive empirical AI and the highly sample-efficient learning mechanisms of human cognition. Investigating these biological paradigms will ultimately serve as a core foundation for designing mathematically principled optimization algorithms and advancing theoretical deep learning.