[ICML 2026] High-accuracy sampling for diffusion models and log-concave distributions

Tiny-diffusion: A minimal implementation of probabilistic diffusion models

Flow Maps: Accelerating Diffusion Model Sampling by Learning the Integral Directly

This article explores flow maps as an alternative to iterative sampling in diffusion models. Instead of taking many small steps to denoise a

Flow Maps: Accelerating Diffusion Model Sampling by Learning the Integral Directly

This article explores flow maps as an alternative to iterative sampling in diffusion models. Instead of taking many small steps to denoise a

Analyzing Loss Functions in Diffusion Bridge Samplers

Diffusion bridges in deep-learning methods for sampling from unnormalized distributions are analyzed, comparing the performance of Log Varia

Core Principles and Mathematical Foundations of Diffusion Models

This monograph presents the core principles of diffusion models, explaining how they work through three complementary mathematical perspecti

Google's DiffusionGemma achieves 4x faster text generation using diffusion-based approach

DiffusionGemma is a new text generation model from Google that achieves up to 4x faster inference speeds compared to traditional autoregress

Google's DiffusionGemma achieves 4x faster text generation using diffusion-based parallel token generation

DiffusionGemma is a new text generation model from Google that achieves up to 4x faster inference speeds compared to traditional autoregress

Google's DiffusionGemma achieves 4x faster text generation using diffusion-based parallel token generation

DiffusionGemma is a new text generation model from Google that achieves up to 4x faster inference speeds compared to traditional autoregress