Embodied AI 101

Episode 66: DiffThinker: Diffusion-based Generative Multimodal Reasoning


Listen Later

# DiffThinker: Diffusion-based Generative Multimodal Reasoning
The legend of AI reasoning has long revolved around humans picturing solutions in their heads – an inherently visual process. Modern AI has made huge strides with models that fuse text and images (so-called **Multimodal LLMs**), suc...
...more
View all episodesView all episodes
Download on the App Store

Embodied AI 101By Shaoqing Tan