Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts
Paper • 2608.20061 • Published • 47
Kakao Brain, Kakao's AI R&D arm, targets global leadership in AI with innovations in generative models like KoGPT (Korean-specialized LLM), Karlo (Text-to-Image), and Kara (radiology report generator).