Skip to content
Hot eventLive

Omni-Diffusion-Distill:统一多模态扩散大语言模型少步蒸馏

1 reports1 sources3 hr ago updated

Get the story

AI overview

2026年10月9日,arXiv Computer Vision(一手)发布 Omni-Diffusion-Distill 框架。该框架为两阶段蒸馏方法,针对统一多模态扩散大语言模型(dLLM)进行少步数蒸馏。报道显示,其将图像生成过程从 128 步压缩至 8 步,将多模态理解过程从 512 步压缩至 64 步,分别获得 18.2 倍和 21.2 倍的 wall-clock 加速。这是目前该事件唯一报道,无更早信息可对比。

Generated from reports · updated 3 hr ago

Timeline

Follow the coverage from different angles.

Oct 9, 2026
  1. arXiv · Computer Vision
    Omni-Diffusion-Distill:统一多模态扩散大语言模型的少步数蒸馏

    Omni-Diffusion-Distill 是一个两阶段蒸馏框架,把统一多模态扩散大语言模型(dLLM)的图像生成从 128 步压缩到 8 步、多模态理解从 512 步压缩到 64 步,分别获得 18.2x 和 21.2x wall-clock 加速。

Heat trend

Current heat 9·Comparable peak 10(Oct 9)·Comparable change over 24 hours –

02.557.510Oct9Oct9Oct9Oct9

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.