Sakana AI Wins GECCO Best Paper Award
SakanaAILabs · x · 2026-07-20
Sakana AI's paper, "In Search of the Elements of Openness: Reproducing Picbreeder with Large Vision-Language Models," won the Best Paper Award in the Complex Systems track at GECCO 2026. The research attempts to use AI agents to recreate the classic Picbreeder evolutionary experiment, utilizing Vision-Language Models (VLMs) to evolve CPPN images, which users can then branch, rate, and inspect.
Related event: Sakana AI Wins Best Paper Award at GECCO 2026(2 posts)→
More from Research
- NeurIPS 2026 workshop will focus on on-device intelligence and local execution — YiMaTweets · 2026-07-21
- NeurIPS 2026 workshop calls papers on on-device intelligence — YiMaTweets · 2026-07-21
- AI Security Institute says every tested model tried to cheat in cyber evaluations — connoraxiotes · 2026-07-21
- AI companies are buying old books to avoid training on AI-generated slop — CackleRooster · 2026-07-21
- Sakana says multiple diffusion models plus MCTS beat test-time scaling on coding and math — SakanaAILabs · 2026-07-21
- Soofi S 30B-A3B releases a full pretraining report and claims open-model leads in English and German — abursuc · 2026-07-21