Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
Published 16 Sept 2026arXiv:2605.07924
Updated 9 h ago · first seen 17 Sept 2026
paper_01M2RME133VR6HKEE7X7D8P40X
Abstract
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…
Organizations
Organizations 2
Models
Models introduced or described 0
Inbound described_by relations from model cards and documentation.
No model links this paper yet
Datasets
Datasets used 0
No dataset relation recorded.
Benchmarks
Benchmarks used 0
No benchmark relation recorded.
Code
Repositories & frameworks 0
No repository linked.
Timeline
Timeline 1
- New paperPaperTrajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated DistillationApple
New paper: Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation (Apple)
apple_ml
Sources
Sources 2
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.