arXiv Artificial Intelligence

Less Uniform Discrete Diffusion is More Powerful and Scalable

2 hours ago 30.09.2026 07:00 👁 2 views
Less Uniform Discrete Diffusion is More Powerful and Scalable

Quick summary

arXiv:2609.35817v1 Announce Type: cross 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 address these, we propose Less Uniform Diffusion (LUDI), a novel UDLM framework. Specifically, we (i) introduce a less uniform loss that directs each reverse transition toward the clean token, and (ii) equip the model with per-token time embeddings that supply token-level corruption hints, enabling conf

Key takeaways

  • arXiv:2609.35817v1 Announce Type: cross 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 address these, we propose Less Uniform Diffusion (LUDI), a novel UDLM framework.

Why it matters

“Less Uniform Discrete Diffusion is More Powerful and Scalable” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗