Intent-Triggered Anchoring for Multi-Token Format Units in Parallel Decoding of Diffusion Language Models
Enter intent-triggered anchoring, a training-free decoding rule that completes a format unit once the model commits its first token, inserting only units with a unique, content-free completion; fallbacks write the unit when the model stops or loops without starting it.
Junhyeok Lee, Kyu Sung Choi
· 0 citations