Normalizing Trajectory Models

Diffusion-based models decompose sampling into many small Gaussian denoising steps, an assumption that breaks down when generation is compressed to a few coarse transitions. Existing few-step methods address this through distillation, consistency training, or adversarial objectives, but sacrifice t…

Read the full story at Apple Machine Learning Research ↗

Timeline · 1 report

1. 2026-10-08 00:00 · Apple Machine Learning Research
   Normalizing Trajectory Models