TEAM: Temporal–Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Acceleration

Diffusion large language models (dLLMs) enable parallel decoding, and recent MoE dLLMs with autoregressive initialization further improve model capacity and accuracy. However, we identify a mismatch between MoE routing and diffusion decoding: a large number of experts are activated at each denoising step, while only a small subset of tokens is ultimately accepted, resulting in substantial inference overhead and limiting their deployment in latency-sensitive applications. In this work, we propose TEAM, a plug-and-play framework that accelerates MoE dLLMs by enabling more accepted tokens with fewer activated experts. TEAM is motivated by the observation that expert routing decisions exhibit strong temporal consistency across denoising levels as well as spatial consistency across token positions. Leveraging these properties, TEAM employs three complementary expert activation and decoding strategies, conservatively selecting necessary experts for decoded and masked tokens and simultaneously performing aggressive speculative exploration across multiple candidates. Experimental results demonstrate that TEAM achieves up to 2.2× speedup over vanilla MoE dLLM, with negligible performance degradation.