Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein Guarantees
stat.ML, cs.LG
Submitted: 2026-06-15
Updated: 2026-10-02
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Building Normalizing Flows with Stochastic Interpolants
- Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
- Assessing the Quality of Denoising Diffusion Models in Wasserstein Distance: Noisy Score and Optimal Bounds
- Wasserstein Convergence of Score-based Generative Models under Semiconvexity and Discontinuous Gradients
- On diffusion-based generative models and their error bounds: The log-concave case with full convergence estimates
- Weak semiconvexity estimates for Schr\"odinger potentials and logarithmic Sobolev inequality for Schr\"odinger bridges
- Projected Langevin dynamics and a gradient flow for entropic optimal transport
- FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generation
- Wasserstein Convergence Guarantees for a General Class of Score-Based Generative Models
- DuoRAT: Towards Simpler Text-to-SQL Models
- Non-asymptotic error bounds for probability flow ODEs under weak log-concavity
- Generative Diffusion Models on Graphs: Methods and Applications
- Rectified Flow: A Marginal Preserving Approach to Optimal Transport
- Finite-Time Analysis of Discrete-Time Stochastic Interpolants
- Hierarchical Text-Conditional Image Generation with CLIP Latents
- An analysis of the noise schedule for score-based generative models
- MoFlow: An Invertible Flow Model for Generating Molecular Graphs
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
- Scalable Posterior Uncertainty for Flexible Density-Based Clustering
- A Transport Geometry of Benign Overfitting
- Efficient quadratic entropy with distance sketches