This post introduces Trajectory-Shaped Discrete Flow Matching (TS-DFM), a method to improve the efficiency and performance of discrete flow matching for text generation. TS-DFM uses a lightweight energy compass to guide the generation process at each step, selecting the most coherent continuations. This training-only shaping significantly reduces the number of forward passes required, leading to substantial speedups and lower perplexity compared to standard discrete diffusion models. The method achieves state-of-the-art performance among discrete generation baselines.
All Apple trails