arXiv cs.LG
· Papers
A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs
arXiv:2603.07475v4 Announce Type: replace-cross Abstract: Autoregressive (AR) language models build representations incrementally via left-to-right prediction, while diffusion language models (dLLMs) are trained through full-sequence denoising. Although recent dLLMs match AR performance, whether diffusion objectives fu