Kyle Fogarty
Hi đź‘‹, I'm Kyle a PhD Student in Computer Science @ University of Cambridge, working with Dr Cengiz Ă–ztireli. I work at the intersection of 3D computer graphics, computer vision, and machine learning, to deliver high fidelity models of visual reality.
Recent Publications:
Zero-Shot Machine Unlearning at Scale via Lipschitz Regularization
To comply with AI and data regulations, the need to forget private or copyrighted information from trained machine learning models...
FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generation
We propose FrePolad: frequency-rectified point latent diffusion, a point cloud generation pipeline integrating a variational autoencoder (VAE) with a denoising...
Neural Fields with Hard Constraints of Arbitrary Differential Order
While deep learning techniques have become extremely popular for solving a broad range of optimization problems, methods to enforce hard...
Neural MLS Surface Reconstruction of Point Clouds
The ability to accurately perceive and model natural structures is a central consideration of many application, including robotic. In this...
Recent Blog Posts:
Computational Toolkit Seminar Series Website
In March 2022, I was invited to give two semninars at the University of Warwick, as part of the Hetsys...
Introduction to Python Course : Build Pong!
2020 was a challenging year for many of us, and that’s why we decided to create a fun and engaging...