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
Efficient One-to-Many Translation with Joint Multi-Stream Diffusion
2026-09-15 04:20
清华发布物理引导的扩散模型，无线信道多尺度预测提升37.19%|TMC'26
2026-09-13 07:02
ReCAST: Reward Credit Assignment across Timesteps for Online Diffusion Reinforcement
2026-09-12 02:41
Fixed State, Long Reach: What a Constant-Size Cache Buys Block Diffusion at Scale
2026-09-10 07:37
The paradox of diffusion distillation (2024)
2026-09-04 01:45
The Loss Floor of Denoising Score Matching: Fisher Geometry from Schr\"odinger Bridges
2026-08-25 07:48