The paper introduces penalty-based and randomized-exploration adaptations to flow matching for improved constraint satisfaction in generative models while matching target distributions.
Constrained diffusion models via dual training
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Constraint-Aware Flow Matching via Randomized Exploration
The paper introduces penalty-based and randomized-exploration adaptations to flow matching for improved constraint satisfaction in generative models while matching target distributions.