I’m a principal scientist at NVIDIA, where I work on Nemotron large language models and previously on Cosmos world foundation models. I publish papers, release open-source deep learning models, and serve as an area chair, workshop organizer, and reviewer at ICLR, CVPR and NeurIPS.

From 2020 to 2022, I was a research scientist at Google Research, where I co-created FILM frame generation, used in Google Photos and Pixel and featured at Google I/O, and TryOnDiffusion, launched on Google Shopping and named among Google’s biggest moments of 2023.

Previously, at NVIDIA Applied Deep Learning Research, led by Bryan Catanzaro, I co-founded and led the frame-generation research behind DLSS 3.0, which boosts gaming frame rates on GeForce RTX GPUs.

Earlier, I was lead inventor and researcher behind Siemens FastSpine, which automatically traces, detects, and numbers the human spine in 3D CT/MRI images.

I earned a PhD in Electrical Engineering from Vanderbilt University, researching image processing for image-guided surgery, and an MS in Computer Vision and Robotics from Heriot-Watt University.