Home / AI Research / Learning Anisotropic Prediction Targets for Flow Models
LEAI Research
Learning Anisotropic Prediction Targets for Flow Models
by StanfordUniversity · Rayhan Zirvi, Hansheng Chen, Gordon Wetzstein, Leonidas Guibas
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. AnisoFlow learns to scale the noise component of the target anisotropically, assigning a separate nonnegative weight to each direction in a jointly learned basis. A closed-form map recovers the velocity from the network's prediction, leaving the architecture, flow-matching loss, and sampler unchanged. Since recovery is exact, training optimizes the target purely to make it easier for theā¦
Upvotes6
Comments2
Published12 Nov 2026