This is huge!

A UCLA team managed to build an optical generative model that runs on light instead of GPUs.

In their demo, a shallow encoder maps noise into phase patterns, which a free-space optical decoder then transforms into images—digits, fashion, butterflies, faces, even… pic.twitter.com/qTz43q3tcI

— 机器之心 JIQIZHIXIN (@jiqizhixin) 2 octobre 2025

This is huge! A UCLA team managed to build an optical generative model that runs on light instead of GPUs. In their demo, a shallow encoder maps noise into phase patterns, which a free-space optical decoder then transforms into images—digits, fashion, butterflies, faces, even

→ View original post on X — @jiqizhixin,