Concept

Diffusion Models

Generative models that create images or audio by iteratively denoising random noise.

A full explainer for this concept is being written. In the meantime, here's what's in the news.

In the news

Normalizing Trajectory Models

Apple ML Research · Oct 8, 2026

Limits of Confidence in Diffusion

Apple ML Research · Oct 2, 2026

DiffuseDrive is filling the data gaps holding back Physical AI

Tech.eu · Sep 23, 2026

How to Guide Your Language Flow

Apple ML Research · Sep 23, 2026

DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models

Apple ML Research · Sep 16, 2026

STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation

Apple ML Research · Aug 25, 2026

Scaling Categorical Flow Maps

Apple ML Research · Aug 7, 2026

Bringing Nunchaku 4-bit Diffusion Inference to Diffusers

Hugging Face · Jul 23, 2026