arXiv Machine Learning June 9, 2026 By Shigui Li, Delu Zeng

Mitigating the Contractivity Trap in Diffusion ODEs via Stein Stabilization

Read the original on arXiv Machine Learning →

arXiv:2606. 07835v1 Announce Type: new Abstract: A fundamental tension exists in the large-step inference of diffusion models via their deterministic probability flow ordinary differential equation (PF-ODE) trajectories, which we identify as the contractivity trap: efficient inference favors large step sizes, while aggressive steps and highly expressive denoisers can undermine contraction-based stability certificates for error suppression.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

diffusion

arXiv Machine Learning

Jul 21

Geometry Adaptive Counterfactual Distribution Learning with Diffusion-Guided Smoothing

arXiv:2605. 25811v2 Announce Type: replace-cross Abstract: We study counterfactual distribution learning for high-dimensional outcomes whose laws may concentrate near lower-dimensional structure.

By Kwangho Kim

rag diffusion

arXiv Machine Learning

Jun 10

It\^o maps for any-step SDEs

arXiv:2606. 11156v1 Announce Type: cross Abstract: Recent one-step generative models accelerate sampling by learning deterministic flow maps of the underlying dynamics.

By Zhengkai Pan, Peter Potaptchik, Wenxi Yao, Michael S. Albergo, Jakiw Pidstrigach

efficiency benchmarks

arXiv Machine Learning

Jun 24

Stabilizing Physics-Informed Consistency Models via Structure-Preserving Training

arXiv:2602. 09303v2 Announce Type: replace Abstract: We propose a physics-informed consistency modeling framework for solving partial differential equations (PDEs) via fast, few-step generative inference.

By Che-Chia Chang, Chen-Yang Dai, Te-Sheng Lin, Ming-Chih Lai, Chieh-Hsin Lai

diffusion fine-tuning

arXiv Machine Learning

Jun 3

A Quantitative Approximation Framework for Flow Distillation in Diffusion Models

arXiv:2606. 03820v1 Announce Type: cross Abstract: We develop a quantitative approximation framework for diffusion distillation, viewing few-step sampling as error propagation under compositions of learned flow maps.

By Weiguo Gao, Ming Li, Lei Shi, Hanfei Zhou

diffusion efficiency multimodal

arXiv Machine Learning

4d ago

Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps

arXiv:2602.12624v2 Announce Type: replace Abstract: Diffusion-based generative models have achieved remarkable performance across various domains, yet their practical deployment is often limited by h...

By Sangwoo Jo, Sungjoon Choi

diffusion benchmarks

arXiv Computer Vision

Aug 21

A Plug-in Interpretation of Conditioning in Score-Based Diffusion Models

arXiv:2608. 19504v1 Announce Type: new Abstract: We propose a conditioning mechanism for diffusion models based on multi-speed joint diffusion of the target and the condition.

By Libo Chen, Souvik Ghosh, Teo Deveney, Chris Budd, Vinay P. Namboodiri

diffusion

One email a morning, machine-written

Related stories

Geometry Adaptive Counterfactual Distribution Learning with Diffusion-Guided Smoothing

It\^o maps for any-step SDEs

Stabilizing Physics-Informed Consistency Models via Structure-Preserving Training

A Quantitative Approximation Framework for Flow Distillation in Diffusion Models

Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps

A Plug-in Interpretation of Conditioning in Score-Based Diffusion Models