3 papers
cs.CV2026
DODO: Discrete OCR Diffusion Models
Sean Man, Gilad Deutch, Roy Ganz +4
Optical Character Recognition (OCR) is a fundamental task for digitizing information, serving as a critical bridge between visual data and textual understanding. While modern Visio…
cs.CV2024
TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models
Gilad Deutch, Rinon Gal, Daniel Garibi +2
Diffusion models have opened the path to a wide range of text-based image editing frameworks. However, these typically build on the multi-step nature of the diffusion backwards pro…
cs.CL2023
In-context Learning and Gradient Descent Revisited
Gilad Deutch, Nadav Magar, Tomer Bar Natan +1
In-context learning (ICL) has shown impressive results in few-shot learning tasks, yet its underlying mechanism is still not fully understood. A recent line of work suggests that I…