Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation

Apple Machine Learningen

Apple Machine Learning

AI Global Wire

Discrete flow matching generates text by iteratively transforming noise tokens into coherent language, but may require hundreds of forward passes. Distillation uses the multi-step trajectory to train a student to reproduce the process in a few steps. When the student underperforms, the usual explanation is insufficient capacity. We argue the opposite: the trajectory is the bottleneck, not the student. Each training trajectory is built through a chain of blind stochastic jumps with no evaluation of sequence quality; a single bad decision at an early midpoint propagates through subsequent steps…

This is a short summary published by AI Global Wire. The full article is owned and hosted by Apple Machine Learning — open it there to read it in full.

Read the full story at Apple Machine Learning
  • Företag

Related AI news