DriftXpress approximates drifting kernels via projected RKHS fields to lower training cost of one-step generative models while matching original FID scores.
Title resolution pending
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
years
2026 9representative citing papers
A new constrained gradient flow on the space of transport maps converges to the OT map and enables more stable and accurate training of convexity-constrained neural networks for learning Monge maps.
Lifts CCCP to Wasserstein space for DC functionals on measures, proves almost stationarity under smoothness/strong-convexity assumptions, and applies to MMD/ED with local convergence and faster empirical runs.
Derives continuous-time finite-particle convergence rates for a new conservative KDE-gradient drifting method and the non-conservative Laplace kernel method in one-step generative modeling.
DFP is a one-step generative policy using Wasserstein gradient flow on a drifting model backbone, with a top-K behavior cloning surrogate, that reaches SOTA on Robomimic and OGBench manipulation tasks.
Training and sampling in static scalar energy generative models are two instances of the same Lyapunov-driven density transport dynamics on Wasserstein space, differing only by initial condition, which yields a finite stopping criterion for Langevin sampling and additive composition rules that keep
The paper interprets GMD algorithms as limiting points of Wasserstein gradient flows on KL divergence with Parzen smoothing and on Sinkhorn divergence, while extending the approach to MMD, sliced Wasserstein, and GAN critics.
citing papers explorer
No citing papers match the current filters.