I am an ML Research Scientist at Scale AI, focusing on expanding LLM capabilities and improving alignment. My previous research includes computer vision, neural radiance fields, and medical image analysis. I did a PhD at MIT CSAIL advised by Polina Golland. I was a student researcher at Google with Daniel Duckworth and Peter Hedman, and interned at Adobe with Jiawen Chen and Cecilia Zhang. I worked with Jim Duncan and Julius Chapiro in the Yale Radiology Research Lab, and as an undergrad I did research with Stuart Campbell.
Selected Publications (full list)
Implicit Representations via Operator Learning Paper | Code | |
InterNeRF: Scaling Radiance Fields via Parameter Interpolation Paper | |
Discretization Invariant Networks for Learning Maps between Neural Fields Project | Paper | Code | |
Dynamic Neural Fields for Learning Atlases of 4D Fetal MRI Time-series Paper | Code | |
Interpolating between Images with Diffusion Models Project | Paper | Code | |
Spatial-Intensity Transforms for Medical Image-to-Image Translation Project | Paper | Code | |
Shape-aware Segmentation of the Placenta in BOLD Fetal MRI Time Series Paper | Code | |
Geometry-Aware Field-to-Field Transformations for 3D Semantic Segmentation Project | Paper | Code | |
Pre-Trained Language Models for Interactive Decision-Making Project | Paper | Code | |
Approximate Discretization Invariance for Deep Learning on Neural Fields Paper | Code | |
Deep learning–assisted differentiation of pathologically proven atypical and typical hepatocellular carcinoma (HCC) versus non-HCC on contrast-enhanced MRI of the liver Paper | |
Spatial-Intensity Transform GANs for High Fidelity Medical Image-to-Image Translation Project | Paper | Video | Code | |
Automated feature quantification of Lipiodol as imaging biomarker to predict therapeutic efficacy of conventional transarterial chemoembolization of liver cancer Paper | Code | |
A probabilistic approach for interpretable deep learning in liver cancer diagnosis Project | Paper | Talk | Code | |
Deep learning for liver tumor diagnosis part II: interpretable deep learning to characterize tumor features Project | Paper | Code | |
Deep learning for liver tumor diagnosis part I: development of a convolutional neural network classifier for multi-phasic MRI Paper | Code | |
The Role of Artificial Intelligence in Interventional Oncology: A Primer Paper | |
Slowing of contractile kinetics by myosin-binding protein C can be explained by its cooperative binding to the thin filament Paper |
Fun AI Creations (more)
<
>