Probability flow ODEs in score-based and reflected diffusion models

arXiv:2610.03846 · stat.ML, cs.LG, math.PR · Submitted 2026-10-02 · Read on arXiv

stat.ML, cs.LG, math.PR

Submitted: 2026-10-02

Updated: 2026-10-02

Comments: 40th Conference on Neural Information Processing Systems (NeurIPS 2026). Workshop: AI for Stochastic Dynamics

Journal ref: 40th Conference on Neural Information Processing Systems (NeurIPS 2026). Workshop: AI for Stochastic Dynamics

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes

Sources

• Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions
• Lipschitz-Guided Design of Interpolation Schedules in Generative Models
• Mimicking diffusion processes with differential equations
• Reflected diffusion, no-flux continuity equations and confined Lagrangian flows in bounded domains
• Linear Convergence of Diffusion Models Under the Manifold Hypothesis

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier