Spherical vMF flows reduce the continuity equation on the sphere to a scalar ODE in cosine similarity, enabling posterior-weighted sampling of categorical sequences via cross-entropy trained posteriors.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
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
-
Spherical Flows for Sampling Categorical Data
Spherical vMF flows reduce the continuity equation on the sphere to a scalar ODE in cosine similarity, enabling posterior-weighted sampling of categorical sequences via cross-entropy trained posteriors.
-
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.