Trendoday

Learning Anisotropic Prediction Targets for Flow Models

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

  • Upvotes5
–Rank now
#18Peak rank
2Days on list
101Score · 7d
Nov 19, 2026First seen
Rank · 7 days

About this paper

AnisoFlow learns an anisotropic, learnable prediction target for flow-based generative models, improving FID and image quality without altering the architecture or sampler.

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 the…

flow-based generative modelsprediction targetvelocitynoise componentclean dataAnisotropic Flow ModelsAnisoFlowlearnable prediction targetanisotropic scalingnonnegative weight
Upvotes
5
Authors
4
Published
Nov 13, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

Learning Anisotropic Prediction Targets for Flow Models was first seen on Hugging Face · Daily papers on Nov 19, 2026. Since then it has appeared in 12 checks on 2 different days. Its best position was #18 of 30, reached on Nov 19, 09:29 UTC. It dropped off the list after Nov 20, 03:29 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 05:2810:5916:2921:5903:29 Nov 19, 05:28 UTC · #19Nov 19, 07:29 UTC · #19Nov 19, 09:29 UTC · #18Nov 19, 11:29 UTC · #20Nov 19, 13:29 UTC · #21Nov 19, 15:29 UTC · #23Nov 19, 17:29 UTC · #25Nov 19, 19:29 UTC · #26Nov 19, 21:29 UTC · #25Nov 19, 23:29 UTC · #26Nov 20, 01:29 UTC · #26Nov 20, 03:29 UTC · #28

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

Platform metric as reported by Hugging Face.

0246 05:2810:5916:2921:5903:29 Nov 19, 05:28 UTC · 5Nov 19, 07:29 UTC · 5Nov 19, 09:29 UTC · 5Nov 19, 11:29 UTC · 5Nov 19, 13:29 UTC · 5Nov 19, 15:29 UTC · 5Nov 19, 17:29 UTC · 5Nov 19, 19:29 UTC · 5Nov 19, 21:29 UTC · 6Nov 19, 23:29 UTC · 6Nov 20, 01:29 UTC · 6Nov 20, 03:29 UTC · 6

Questions

Is Learning Anisotropic Prediction Targets for Flow Models trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 20, 03:29 UTC, after 2 days of trending.

What is the highest rank Learning Anisotropic Prediction Targets for Flow Models reached?

#18 on Hugging Face · Daily papers, on Nov 19, 09:29 UTC. Trendoday checks this list every 120 minutes.

How long has Learning Anisotropic Prediction Targets for Flow Models been trending?

It was first seen on Nov 19, 2026 and has been on the list on 2 days (12 checks) since.