AI RESEARCH
Continuous Diffusion Scales Competitively with Discrete Diffusion for Language
arXiv CS.LG
•
ArXi:2605.18530v1 Announce Type: cross While diffusion has drawn considerable recent attention from the language modeling community, continuous diffusion has appeared less scalable than discrete approaches. To challenge this belief we revisit Plaid, a likelihood-based continuous diffusion language model (DLM), and construct RePlaid by aligning the architecture of Plaid with modern discrete DLMs.