Diffusion models have significantly advanced the fields of image, audio, and video generation, but they depend on an iterative sampling process that causes slow generation.
本文为英文原文，点击下方按钮一键翻译为中文。
相关推荐
The paradox of diffusion distillation (2024)
2026-09-04 01:45
The Loss Floor of Denoising Score Matching: Fisher Geometry from Schr\"odinger Bridges
2026-08-26 12:00
A Theory of Speciation in Generative Diffusion Models on Compact Riemannian Manifolds
2026-08-26 12:00
DiffusionGemma Technical Report
2026-08-20 21:24
Coarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems
2026-08-18 12:00
Simplifying, stabilizing, and scaling continuous-time consistency models
2024-10-23 18:00