About

Hello! I am a third-year computer science PhD candidate 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. I've worked on interpretability and compression for large visual foundation models, and I have extensive experience training large transformer-based vision models. I've also done work at the intersection of neuroscience and AI, building computational models of traveling waves to study how neurons transfer information.

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.*, Fel T.*, Hakim R.*, Brondetta A., Ba D., Keller TA. (2025).
   Block-Recurrent Dynamics in ViTs
   Under review.

   We introduce the Block-Recurrent Hypothesis (BRH), arguing that trained ViTs admit a block-recurrent depth structure. To validate this, we train recurrent surrogates called Raptor. We demonstrate that a Raptor model can recover 96% of DINOv2 ImageNet-1k linear probe accuracy in only 2 blocks while maintaining equivalent computational cost.

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

Resume

You can find my resume here.

Contact

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