🤖🧪About Me
I’m a research scientist at Biohub building foundation models and ML infrastructure for biological imaging—focusing on 3D methods for understanding cellular structure from microscopy data.
Recent work includes: Led the CZII CryoET Object Identification competition on Kaggle (published in Nature Methods, 1200+ participating teams). Built CryoLens, a generative model for learning interpretable 3D representations from cryo-electron tomography data. Created the copick ecosystem for collaborative annotation and data management in cryo-electron tomography.
I serve on napari’s steering council and have built multiple open-source tools: sciview (3D/VR for ImageJ), SNT (neuron tracing and morphology analysis), and album (reproducible scientific workflows).
Background: Led research teams at Oak Ridge National Lab and Max DelbrĂĽck Center Berlin. Advised DARPA programs in lifelong learning and adversarial ML. PhD from Brandeis (computer science + quantitative biology), postdoc at Harvard Medical School.
- 3D and volumetric deep learning
- Foundation models for microscopy
- Open-source scientific software
- Biological image analysis
Postdoctoral Fellow, Pathology
Harvard Medical School
PhD Computer Science
Brandeis University
MA Computer Science
Brandeis University
BA
Hampshire College
I work on three-dimensional dynamic living systems — how cells and tissues are organized in space, and how that organization forms and changes over time.
The methods I build for this are generative and differentiable: generative models of 3D cellular structure, neural rendering, and differentiable gene regulatory networks that bring gradient-based learning to models of development. Applied to volumetric microscopy, including cryo-electron tomography, these yield learned representations of structure rather than hand-designed ones.
That work grows out of a longer line: evolutionary and agent-based models of morphogenesis, angiogenesis, and collective behavior; gene regulatory networks for control and adaptation; real-time 3D and VR rendering for microscopy; whole-brain lightsheet imaging in zebrafish; and neuron reconstruction and morphometry. Much of it is released as open-source software — napari, SciView, SNT, copick, album — in daily use across the bioimaging community.
A curated selection.
Tools and models I have built, several of which are in active use by the bioimaging community.
