Creating engaging Video-to-Video and Image-to-Video experiences by developing and optimizing efficient generative models, with a focus on low-latency, production-scale deployment. Work spans the full lifecycle, including large-scale data curation, architecture design, and advanced post-training distillation techniques to retain quality while significantly reducing compute.

Course: Advanced Computer Vision (16-820).

Instructor: Prof. David Held

This is a new Ph.D.-level course wherein I am involved in preparing and reviewing the assignments, maintaining the course website, holding Office Hours, and helping students with the theory and code of concepts covered throughout the course.

Advised by Prof. Kris Kitani to build a low-power Visual-Inertial Odometry module for AR glasses.

Course: Machine Learning (10-601)

Instructor: Prof. Matt Gormley

Preparing and suggesting exam and assignment problems, and material in order to make the course more effective. Holding recitations and office hours for students.