Hugging Face Papers ↗ · 2026-11-13
Learning Anisotropic Prediction Targets for Flow Models
Media reports Hugging Face Papers Source language: Chinese
Excerpt
论文摘要(作者报告,未经本站复测):Flow-based generative models are trained on a hand-chosen prediction target, such as the velocity, the noise, or the clean data. This choice strongly affects training and sample quality. We introduce Anisotropic Flow Models (AnisoFlow), which replaces a fixed prediction target with a fully learnable one.
Short excerpt from the source — open the original for the full text.