Less Uniform Discrete Diffusion is More Powerful and Scalable
arXiv:2609.35817v1 Announce Type: new Abstract: Although uniform diffusion language models (UDLMs) represent a promising diffusion paradigm, scaling them remains challenging. We identify the core obstacle as an over-uniform training objective and condition-target confusion during sampling. To addre…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-01 04:00 · arXiv cs.CL
Less Uniform Discrete Diffusion is More Powerful and Scalable