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

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.

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.

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.

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

Cloned from here!