W-Flow achieves state-of-the-art one-step ImageNet 256x256 generation at 1.29 FID by training a static neural network to follow a Wasserstein gradient flow that minimizes Sinkhorn divergence, delivering roughly 100x faster sampling than comparable multi-step models.
Sinkhorn-drifting generative models
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
years
2026 9representative citing papers
For companion-elliptic kernels vanishing drifting fields identify target measures exactly, and field convergence yields weak convergence once mass escape to infinity is detected by a single C0 scalar.
SROT regularizes the OT plan toward a smoothened sliced OT plan, producing more accurate approximations to exact OT than entropic OT while also improving on the sliced OT reference.
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.
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.
SymDrift makes drifting models produce symmetry-invariant samples in one step via symmetrized coordinate drifts or G-invariant embeddings, outperforming prior one-shot baselines on molecular benchmarks and cutting compute by up to 40x.
RA-OT and OA-OT amortize optimal transport by regressing or optimizing sliced-OT Kantorovich potentials to approximate full OT plans efficiently across multiple measure pairs.
A simplified one-step diffusion distillation uses pretrained teacher features directly for drifting loss plus a mode coverage term, achieving FID 1.58 on ImageNet-64 and 18.4 on SDXL.
GMD algorithms correspond to limiting points of Wasserstein gradient flows on the KL divergence with Parzen smoothing and bear resemblance to Sinkhorn divergence fixed points, with extensions to MMD and other divergences.
citing papers explorer
-
One-Step Generative Modeling via Wasserstein Gradient Flows
W-Flow achieves state-of-the-art one-step ImageNet 256x256 generation at 1.29 FID by training a static neural network to follow a Wasserstein gradient flow that minimizes Sinkhorn divergence, delivering roughly 100x faster sampling than comparable multi-step models.
-
Identifiability and Stability of Generative Drifting with Companion-Elliptic Kernel Families
For companion-elliptic kernels vanishing drifting fields identify target measures exactly, and field convergence yields weak convergence once mass escape to infinity is detected by a single C0 scalar.
-
Sliced-Regularized Optimal Transport
SROT regularizes the OT plan toward a smoothened sliced OT plan, producing more accurate approximations to exact OT than entropic OT while also improving on the sliced OT reference.
-
Learning Monge maps with constrained drifting models
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.
-
Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow
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.
-
SymDrift: One-Shot Generative Modeling under Symmetries
SymDrift makes drifting models produce symmetry-invariant samples in one step via symmetrized coordinate drifts or G-invariant embeddings, outperforming prior one-shot baselines on molecular benchmarks and cutting compute by up to 40x.
-
Amortized Optimal Transport from Sliced Potentials
RA-OT and OA-OT amortize optimal transport by regressing or optimizing sliced-OT Kantorovich potentials to approximate full OT plans efficiently across multiple measure pairs.
-
Teacher-Feature Drifting: One-Step Diffusion Distillation with Pretrained Diffusion Representations
A simplified one-step diffusion distillation uses pretrained teacher features directly for drifting loss plus a mode coverage term, achieving FID 1.58 on ImageNet-64 and 18.4 on SDXL.
-
On the Wasserstein Gradient Flow Interpretation of Drifting Models
GMD algorithms correspond to limiting points of Wasserstein gradient flows on the KL divergence with Parzen smoothing and bear resemblance to Sinkhorn divergence fixed points, with extensions to MMD and other divergences.