About

Hello! I am a first-year computer science PhD student at Harvard University, advised by Professor Demba Ba. I am supported by the Kempner Institute Graduate Fellowship. My research interests are primarily in computer vision and generative modeling. Previously, I worked at the AI Institute in Dynamic Systems with Nathan Kutz and Ryan Raut. I earned my B.S. in computer science from the Allen School at the University of Washington, where I worked with Rajesh Rao and William Noble.

Contact

LinkedIn: mozesjacobs
Email: mozesjacobs [at] g.harvard.edu

Projects

HyperSINDy

Gradient Origin Predictive Coding

I did my Undergraduate Honors Thesis, ``Gradient Origin Predictive Coding'', under Dr. Rajesh Rao. In short, I created an encoder-less VAE that performed inference using the gradient of the variational loss. You can find the thesis document here.