Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.
arXiv preprint arXiv:2110.02999 , year =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
A single-network fixed-point formulation for neural optimal transport eliminates adversarial min-max optimization and implicit differentiation while enforcing dual feasibility exactly.
Semi-dual OT formulation has degenerate saddle-point structure; necessary and sufficient conditions for Monge map convergence are derived without requiring dual potential optimality.
citing papers explorer
-
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.
-
Fixed-Point Neural Optimal Transport without Implicit Differentiation
A single-network fixed-point formulation for neural optimal transport eliminates adversarial min-max optimization and implicit differentiation while enforcing dual feasibility exactly.
-
Stability of the Monge Map in Semi-Dual Optimal Transport
Semi-dual OT formulation has degenerate saddle-point structure; necessary and sufficient conditions for Monge map convergence are derived without requiring dual potential optimality.