Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 15, 2026MathematicsOpen Access

Product Manifold Flow Matching: Low-NFE Generative Efficiency and Domain-Dependent Finite-Step Quality Optima

View Full Paper
Ask AI
Bookmark
Share

Authors

HJHong-Seok JangYCYoungtaek ChaSCSungjoon Choi

Discussion

Loading...

Member takes

Overview

Empirical evaluation demonstrates low-step generative gains via target-speed reweighting in image models, indicating that mathematical refinement diverges from sample quality.

Key Points

  • Investigate why generative flow quality does not improve monotonically with finer numerical integration in Product Manifold Flow Matching and identify the mechanisms driving low-step performance.
  • Trained 32 M and 129 M parameter flow-matching models on CIFAR-100 and a synthetic pile-driver dataset using products of hyperbolic factor spaces with exponential-map Euler updates.
  • Evaluated generative fidelity across varying numbers of function evaluations (NFEs) against standard Euclidean baselines across multiple architecture-seed configurations.
  • Conducted factor-wise ablation studies isolating the influence of geometric curvature from target-speed reweighting mechanisms.
  • Product models at NFE = 4 achieved lower FID than Euclidean baselines at NFE = 32 across all six architecture-seed configurations, reducing sampling time by approximately eightfold.
  • Applying factor-wise target-speed reweighting to Euclidean baselines replicated the low-NFE advantage across three seeds, whereas omitting it from Product models degraded FID at NFE ≥ 4.
  • FID reached optimal scores at NFE = 8 on CIFAR-100 and NFE = 4 on the synthetic dataset, despite continuous decreases in numerical integration errors at higher step counts.

Cite This Study

Jang et al. (2026) studied this question.

synapsesocial.com/papers/6aa913609013453be30a1421https://doi.org/10.3390/math14183333
View Full Paper
Ask AI
Bookmark
Share