Jacob Yeung

Hello! I am a second-year Ph.D. student in the Neural Computation & Machine Learning joint Ph.D. program at Carnegie Mellon University supported by an NSF Graduate Research Fellowship. I am advised by Prof. Michael Tarr and Prof. Deva Ramanan.

My primary interests lie in understanding how humans understand dynamic visual stimuli and improving machine visual reasoning.

I graduated with a B.S. in Electrical Engineering and Computer Science (EECS) from UC Berkeley. My research was advised by Dr. Kristofer Bouchard and Dr. Ji Hyun Bak at the Lawrence Berkeley National Laboratory. I also worked with Medhini Narasimhan and Prof. Trevor Darrell at Berkeley AI Research (BAIR).

Email  /  Github  /  LinkedIn

profile photo
Research
brain-nerds photo Reanimating Images using Neural Representations of Dynamic Stimuli
Jacob Yeung, Andrew F. Luo, Gabriel Sarch, Margaret M. Henderson, Deva Ramanan, Michael J. Tarr
CVPR 2025
Paper / bibtex

We propose a way to study visual motion in the brain by decoupling the modeling of static image representations and motion representations in the human brain.

brainsail photo Brain Mapping with Dense Features: Grounding Cortical Semantic Selectivity in Natural Images With Vision Transformers
Andrew F. Luo, Jacob Yeung, Rushikesh Zawar, Shaurya Dewan, Margaret M. Henderson, Leila Wehbe, Michael J. Tarr
ICLR 2025
Paper / bibtex

We propose an efficient gradient-free distillation module capable of extraction high quality dense CLIP embeddings, and utilize these embeddings to understand semantic selectivity in the visual cortex.

edca formulation photo Discovery of Linked Neural and Behavioral Subspaces with External Dynamic Components Analysis
Jacob Yeung, Ji Hyun Bak, Kristofer Bouchard
COSYNE, 2023
Paper / Poster

We introduce external Dynamics Components Analysis (eDCA), a linear dimensionality reduction method that finds subspaces of past neural data that have maximal mutual information with subspaces of future behavior data.

hangul fonts photo Hangul Fonts Dataset: a Hierarchical and Compositional Dataset for Investigating Learned Representations
Jesse Livezey, Ahyeon Hwang, Jacob Yeung, Kristofer Bouchard
International Conference on Image Analysis and Processing, 2022
Paper / bibtex

We introduce a dataset with known hierarchical and compositional structure and show deep unsupervised models poorly learn the latent generative structures.

Teaching

I have been a teaching assistant for the following courses:

I have been a tutor for the following courses: