Open-weight & owned stack · Training tuning

Decoupled DMD Distills Diffusion Models Into Few Steps

Sep 12, 2026

An ICLR 2026 paper introduced Decoupled DMD, combining classifier-free-guidance augmentation with distribution matching for few-step and single-step generation.

Read the original at mlanthology.orgOpens the publisher's site in a new tab

More in Open-weight & owned stack

Z.ai publishes GLM-5.3 open weightsSep 8 MiniMax H3 highlighted as open-weight multimodal modelSep 7 InternLM releases 397B multimodal Intern-S2 modelSep 13 DeepSeek Model Nearly Matches GPT-6 Astra DesignSep 10 DeepSeek presents V4 FlashSep 8