Diffusion Language Models Know the Answer Before Decoding

ArXi:2508.19982v5 Announce Type: replace Diffusion language models (DLMs) have recently emerged as an alternative to autoregressive approaches, offering parallel sequence generation and flexible token orders. However, their inference remains slower than that of autoregressive models, primarily due to the cost of bidirectional attention and the large number of refinement steps required for high quality outputs.