Mozes Jacobs

Logo

View My GitHub Profile

About

Hello! I am a second-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. I'm also interested by exploring how ideas in theoretical neuroscience can augment vision models. I'm specifically interested in object-centric learning, the binding problem, and compositional generalization in vision models. 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.

Publications and Preprints

  1. Jacobs, M., Budzinski RC., Muller L., Ba D., Keller TA. (2025).
    Traveling Waves Integrate Spatial Information Intro Spectral Representations
    To appear at the ICLR 2025 Re-Align Workshop.
  2. Jacobs, M., Budzinski RC., Muller L., Ba D., Keller TA. (2025).
    Traveling Waves Integrate Spatial Information Through Time
  3. Jacobs, M., Brunton BW., Brunton SL., Kutz JN., Raut RV. (2023).
    HyperSINDY: Deep Generative Modeling of Nonlinear Stochastic Governing Equations
  4. Jacobs, M., Jiang LP., Rao RP. (2022).
    Gradient Original Predictive Coding
    Undergraduate senior thesis.

Resume

You can find my resume here.

Contact

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