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 by the expert-routing decisions of a Mixture-of-Experts backbone, without increasing active parameters over the factorized baseline. Across synthetic multi-modal benchmarks, binarized MNIST, and LM1B, E-MoE improves few-step generation over factorized baselines, addressing the posterior collapse that plagues prior continuous Gaussian latent approaches. arXiv:2609.37533v1 Announce Type: new Abstract: Masked diffusion models MDMs generate sequences by progressively unmasking several tokens per denoising step, but their reverse process is typically factorized over positions, limiting sample quality in the few-step regime where diffusion's speed advantage over autoregressive decoding matters most. A recent line of work introduces a continuous Gaussian latent, trained as a variational autoencoder, to capture correlations across positions, but such approaches are prone to posterior collapse, where the latent is silently ignored. We propose Enhanced Mixture-of-Experts E-MoE , which builds the reverse process as a mixture of factorized distributions over a discrete shared latent given by the expert-routing decisions of a Mixture-of-Experts MoE backbone, without increasing active parameters over the factorized baseline. Across synthetic multi-modal benchmarks, binarized MNIST, and LM1B, E-MoE improves few-step generation over factorized baselines.