I build machine vision methods that biomedical practitioners can use as-is to understand their data without needing to retrain or adapt to their use-cases. I’m broadly interested in questions that can be answered by constructing new imaging datasets, real or otherwise.
I am currently an investigator and faculty member at the A. A. Martinos Center for Biomedical Imaging at Harvard Medical School and Massachusetts General Hospital. Before that, I was a postdoc at MIT CSAIL in Polina Golland’s Medical Vision Group where I worked on representation learning frameworks for automatic generalization to entirely new tasks, biomedical contexts, and datasets (the trick was writing our own data engines).
I got my Ph.D. from NYU under Guido Gerig at the VIDA Center where I worked on generative models and inverse problems in medical image analysis contexts.
Recent updates
| 04/26 | New work (led by Sebo) shows how to train networks that generalize across domain shifts with just 3 extra lines of code. |
| 12/25 | I’ll area chair ECCV 2026 this spring. |
| 09/25 | I’ll area chair CVPR 2026, MIDL 2026, and ML4H 2025 this fall. |
| 09/25 | Our new NeurIPS 2025 paper, led by Vivek, enables aligning intraoperative X-rays to preop CTs despite any articulated skeletal motion. Also, has the one of the nicest Figure 1s you’ll see this year :) |
| 04/25 | New at ICLR 2025! Using random compositions of templates to drive a self-supervised objective, we derive entirely general-purpose representations that yield SOTA 3D registration and segmentation. |
| 03/25 | At CVPR 2025, led by Maz: instead of waiting a week each time we want deformable templates of collections of volumes, we can now predict them in a single forward pass for any unseen brain dataset. |
| 03/25 | In xvr, Vivek figured out how to train subject-specific neural networks for 2D X-ray to 3D CT registration in ~5 mins with sub-millimeter accuracy (and built a whole library around it). |
| 09/24 | New at NeurIPS 2024: fast equivariant modeling of spatio-spherical data leads to SOTA neuronal fiber tracking in diffusion MRI (led by Axel). |