Scaling Texttoimage Diffusion Transformers With Representation Autoencoders

1 mentions across 1 person

All mentions

Yann LeCun

paper · 2026-01-22

Recommended

“Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders”

Representation Autoencoders Outperform VAEs in Large-Scale Text-to-Image Generat ↗