SOURCE-LINKED INTELLIGENCE

Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Discrete diffusion and flow models are a promising alternative to autoregressive language models, but compressing many-step sampling into fewer steps typically requires distilling a pretrained teacher model. This caps the student at the teacher's quality and requires a costly two-stage training pipeline. We introduce Discrete Beckmann Transport Models (DBTM), built on a time-independent flow whose autonomous transport map provably carries any point in the ambient space to a fixed point on the vertices of the simplex in a single step. We show that this fixed-point property is characterized by a

Read original source ↗ Open in workspace

recordType

paper

region

Global