PiFM extends Flow Matching to multi-parameter settings by enforcing path-independent flows that approximate Wasserstein barycenters under suitable assumptions.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Complex normalizing flows nearly correspond to information Kähler-Ricci flows because the log-determinant term matches Ricci curvature under differentiation, recovering a Kähler-Ricci variation in the continuum limit.
Categorical flow matching models scale to 1.7B parameters on 2.1T tokens, enabling 4-step text generation with competitive quality and benchmark performance.
citing papers explorer
-
Path-independent Flow Matching for Multi-parameter Generative Dynamics
PiFM extends Flow Matching to multi-parameter settings by enforcing path-independent flows that approximate Wasserstein barycenters under suitable assumptions.
-
Complex normalizing flows can almost be information K\"ahler-Ricci flows
Complex normalizing flows nearly correspond to information Kähler-Ricci flows because the log-determinant term matches Ricci curvature under differentiation, recovering a Kähler-Ricci variation in the continuum limit.
-
Scaling Categorical Flow Maps
Categorical flow matching models scale to 1.7B parameters on 2.1T tokens, enabling 4-step text generation with competitive quality and benchmark performance.