04:00
2026-09-30
machinebrief.com
artificial-intelligence
E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models
E-MoE, a new method from researchers behind arXiv paper 2609.37533v1, builds the reverse process of masked diffusion models as a mixture of factorized distributions over a discrete shared latent set b…