trace-based

Tag

Cards List
#trace-based

Trace-Based On-Policy Distillation for Masked Diffusion Language Models

arXiv cs.CL · 19h ago Cached

A paper proposing Trace-Based On-Policy Distillation (TOPD), a teacher-supervised framework for transferring reasoning abilities to masked diffusion language models without reward estimation, achieving comparable accuracy to RL-trained counterparts with significant compute speedup.

0 favorites 0 likes
← Back to home

Submit Feedback