45 min
Seminar, Hosted by Simons Institute for the Theory of Computing
What Really Separates Autoregression and Diffusion? A Synthesis and Path Beyond
Meta
Recording
Abstract
Masked diffusion provides a common lens for comparing autoregressive and diffusion-based generation. This talk argues that observed differences in parallelism and perceptual quality can follow from training and specification choices rather than a fundamental divide. It then studies adaptive generation orders, insertion-based planning and scalable maximum-likelihood learning beyond fixed or random ordering.