#artificial intelligence
May 2026
Continuous Diffusion Scales Competitively with Discrete Diffusion for Language
The first scaling law for continuous DLMs that rivals discrete DLMs is established: RePlaid exhibits a compute gap of only $20\times$ compared to autoregressive models, outperforms Duo while using fewer parameters, and outperforms MDLM in the over-trained regime.
Zhi-Han Yang, Wei Guo, Shuibai Zhang et al.
· arXiv.org · 12 citations
· ⚡2