KLASS: KL-Guided Fast Inference in Masked Diffusion Models Paper • 2511.05664 • Published Nov 7 • 35
Hybrid Architectures for Language Models: Systematic Analysis and Design Insights Paper • 2510.04800 • Published Oct 6 • 36
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation Paper • 2507.10524 • Published Jul 14 • 70
DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs Paper • 2503.07067 • Published Mar 10 • 31