Diffusion Language Models: Foundations, Efficiency, and Reasoning

Researchers compare diffusion-based language generation with autoregressive decoding. The workshop examines discrete noising and denoising, bidirectional context, controllability, efficiency and reasoning, bringing theoretical methods into conversation with the practical challenges of training and deploying these models. Session: 08:00–17:00 (Australia/Sydney). A paid NeurIPS virtual pass includes workshop livestreams; on-site access follows the host-location registration rules.