跳到正文
原文
theworldlabs· @theworldlabs · X·· 2026-09-02AI 评分38

World Labs统一多模态自回归扩散架构

AI 导读

所有这些都由一个统一架构驱动:一个从零预训练的多模态自回归扩散 Transformer。 这一基础融合了现代 LLM 和视频模型的优势,受益于这两个领域的架构、算法和系统进步。

正文 · 原文

All of this is powered by one unified architecture: a multimodal autoregressive diffusion transformer, pretrained from scratch.

This foundation blends the best of modern LLMs and video models, benefiting from the architectural, algorithmic, and systems advances from both areas.

来源:theworldlabs · x.com