Controllable Diversity in AI Image Generation

Researchers propose Semantic Browsing, a method for controllable diversity in image generation that structures output variations based on meaningful design choices rather than incidental factors.

One continuously updated timeline instead of dozens of separate articles. New developments are appended as the story evolves.

1. AnnouncementJun 22, 2026, 05:59 PM 84%

   Researchers propose Semantic Browsing to enable structured, controllable diversity in text-to-image models

   Researchers propose Semantic Browsing, a method for controllable diversity in image generation that structures output variations based on meaningful design choices rather than incidental factors.

   Read the full story →