E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models

Arseny Ivanov, Alexander Kolesov, Alexander Korotin, Ivan Oseledets, Mikhail Goncharov

E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models: 61 upvotes on Hugging Face Daily Papers, #17 of 84 papers on 2026-10-02. Day-by-day upvote history.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.