| title | Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation |
|---|---|
| authors | Amin Karimi Monsefi, Dominic Culver, Nikhil Bhendawade, Manuel R. Ciosici, Yizhe Zhang, Irina Belousova |
| date | 2026-05-08 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.07924 |
| affiliation | Apple |
| upvotes | 3 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| 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, yet the student must imitate the result. Trajectory-Shaped Discrete Flow Matching (TS-DFM) replaces these blind jumps with guided navigation: a lightweight energy compass evaluates candidate continuations at each midpoint, selecting the most coherent. All shaping is training-only; inference cost is unchanged. On 170M-parameter language modeling, the shaped student at 8 steps achieves 32% lower perplexity than the 1,024-step teacher while being 128x faster, with gains consistent across source distributions and three evaluators of increasing scale. TS-DFM achieves the best perplexity of any discrete-generation baseline we compare against, including methods trained on 6x more data or using 5x larger models. |
cite
@misc{monsefi2026trajectory,
title={Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation},
author={Amin Karimi Monsefi and Dominic Culver and Nikhil Bhendawade and Manuel R. Ciosici and Yizhe Zhang and Irina Belousova},
year={2026},
eprint={2605.07924},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.07924}
}