AI RESEARCH
SAID: Accelerating Diffusion-Based Language Models via Scaffold-Aware Iterative Decoding
arXiv CS.CL
•
ArXi:2606.04974v1 Announce Type: new Diffusion large language models (DLLMs) enable non-autoregressive generation by iteratively denoising corrupted token sequences with bidirectional context. Despite their ability to update multiple positions in parallel, inference remains costly due to the many denoising steps required for high-quality generation. We propose SAID, a Scaffold-Aware Iterative Decoding framework that accelerates DLLMs by reallocating computation across tokens.