alphaXiv(@askalphaxiv):“Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning” Few-step diffusion and flow LMs usually require distilling a pretrained teacher, which adds training cost and caps the student at teacher quality. So this paper learns a direct path from noise to discrete tokens, generating the whole sequence in one step without a teacher model or tracking diffusion time. Then when you add extra steps, the model doesn’t just take smaller steps toward an answer. It revisits uncertain tokens and fixes them using the tokens it’s already confident about.

2026.09.16 08:29

“Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning” Few-step diffusion and flow LMs usually require distilling a pretrained teacher, which adds training cost and caps the student at teacher quality. So this paper learns a direct path from noise to discrete tokens, generating the whole sequence in one step without a teacher model or tracking diffusion time. Then when you add extra steps, the model doesn’t just take smaller steps toward an answer. It revisits uncertain tokens and fixes them using the tokens it’s already confident about.

显示更多