Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training Paper • 2503.18929 • Published 10 days ago • 3 • 2
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data Paper • 2410.18558 • Published Oct 24, 2024 • 20 • 2