AI RESEARCH
TEAM: Temporal-Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Acceleration
arXiv CS.CL
•
ArXi:2602.08404v2 Announce Type: replace Diffusion large language models (dLLMs) have recently gained significant attention due to their inherent for parallel decoding. Building on this paradigm, Mixture-of-Experts (MoE) dLLMs with autoregressive (AR) initialization have further nstrated strong performance competitive with mainstream AR models. However, we identify a fundamental mismatch between MoE architectures and diffusion-based decoding.