Diffusion models

Software / App

Models originally introduced for image generation that learn to reverse a process of gradually adding noise to data, enabling sampling from complex distributions. They are powerful for representing multimodal distributions.

Mentioned in 1 video

Videos Mentioning Diffusion models

Stanford AA203 Optimal and Learning-Based Control | Spring 2026 | Lecture 15: Imitation Learning

Stanford AA203 Optimal and Learning-Based Control | Spring 2026 | Lecture 15: Imitation Learning

Stanford Online

Models originally introduced for image generation that learn to reverse a process of gradually adding noise to data, enabling sampling from complex distributions. They are powerful for representing multimodal distributions.