About Me

Hi, I am a Ph.D. candidate in the Dept. of Psychology at Harvard University, advised by Prof. George Alvarez and Prof. Talia Konkle. I am grateful to be supported by the Graduate Fellowship at the Kempner Institute for the Study of Natural and Artificial Vision. Currently, I’m a Research Fellow at Goodfire .

Broadly, I study how the human visual system transforms raw sensory input into structured, meaningful representations and how we can uncover similar mechanisms inside large-scale vision models. My work bridges cognitive science, computational vision, and interpretability to understand object perception: how local elements are organized and grouped into proto-objects, how information flows through long-range interactions, and how holistic global shape ultimately emerges.

On the cognitive and computational side, I study whether self-supervised learning and vision-language alignment provide the inductive biases to learn holistic shape and human-like sensitivity to configural relations between object parts.
On the interpretability side, we build a decomposition framework that separates positional and semantic information in Vision Transformers via spectral factorization of the query–key interaction, allowing us to isolate the circuits that govern internal information flow.
On the brain/neural side, I examine the tuning and topographic organization of visual representations in humans and vision models, characterizing how perceptual grouping mechanisms (e.g., contour integration) emerge and spatially organize via self-organizing constraints.