Joint Attention

Concept

A method to inject conditions where both image patch embeddings and text embeddings are considered jointly and attended through the same self-attention layer.

Mentioned in 1 video

Videos Mentioning Joint Attention

Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 5 - Architectures

Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 5 - Architectures

Stanford Online

A method to inject conditions where both image patch embeddings and text embeddings are considered jointly and attended through the same self-attention layer.