Kate Feingold
I am a PhD student in Computer Vision at the Weizmann Institute of Science, advised by Prof. Tali Dekel, with whom I also completed my M.Sc. I hold a B.Sc. from Taras Shevchenko National University.
My research sits at the intersection of generative models, 3D/4D perception, and multimodal learning. I am drawn to problems where vision meets other modalities or paradigms in creative tasks.
Before joining Weizmann, I spent over six years working in computer vision and deep learning across industry, including at Deci AI (acquired by NVIDIA), where I contributed to a Neural Architecture Search system and to the open-source library SuperGradients, with earlier work spanning UAV navigation, action recognition, and video understanding.
Publications
-
Match-and-Fuse: Leveraging Text-To-Image Diffusion Models for Consistent Set-to-Set Generation
Talks
- "Leveraging Text-To-Image Diffusion Models for Consistent Set-to-Set Generation"
Amazon Prime Video Sports Reading Group, January 2026 - "Leveraging Text-To-Image Diffusion Models for Consistent Set-to-Set Generation"
AI Center General Meeting, Weizmann Institute of Science, April 2026
Blog
- A Comprehensive Overview of Gaussian Splatting — featured as #1 trending on Medium, December 2023
- Vision Transformer (ViT) Under the Magnifying Glass
Teaching
- Teaching Assistant, Advanced Topics in Computer Vision and Deep Learning
Weizmann Institute of Science — 2024, 2025, 2026