arXiv Machine Learning
Jun 9
Midpoint Generative Models
arXiv:2605. 29920v2 Announce Type: replace Abstract: We introduce Midpoint Generative Models (MGM), a principled framework for training one-step generative models.
Unifying Generative Models with Path Integrals
arXiv:2608. 12438v1 Announce Type: new Abstract: We formulate generative modeling as a path integral in which flow-based, diffusion-based, variational, and adversarial models arise as different evaluation principles for a single master action.
Related stories
arXiv Machine Learning
Jun 9
Self-Consistent Generative Paths via Admissible Random Variational Transport
arXiv:2606. 08953v1 Announce Type: new Abstract: Modern generative models often define an entire probability path from a simple prior to the data law, rather than only an endpoint map.
arXiv Machine Learning
Jun 2
Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching
arXiv:2605. 00941v4 Announce Type: replace Abstract: Flow matching has become a leading framework for generative modeling, but quantifying the uncertainty of its samples remains an open problem.
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.
arXiv Machine Learning
Jul 22
ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling
arXiv:2607. 19332v1 Announce Type: new Abstract: Generative models have undergone many generations of evolution, from VAEs/GANs to diffusion/flow matching.
Hugging Face Trending Papers
Jul 21
ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling
Generative models have undergone many generations of evolution, from VAEs/GANs to diffusion/flow matching. Along the way, the underlying techniques have become more complicated and various beliefs about what drives strong empirical performance have taken hold.
arXiv AI
Aug 11
Renormalising Generative Models for Active Inference: Foundations, Derivations, and Verification
arXiv:2608. 09512v1 Announce Type: new Abstract: Active inference offers a unified framework for perception, learning, and action, but scaling discrete active-inference models to rich spatial and temporal domains remains difficult.
arXiv Machine Learning
Jun 30
The Fundamental Limits of Valid Transport Map Estimation
arXiv:2606. 30574v1 Announce Type: new Abstract: Many modern generative modeling methods, including diffusion models, normalizing flows, and flow matching, estimate transport maps or plans between distributions without explicitly targeting an optimal transport (OT) map.
arXiv Machine Learning
Jul 7
Non-Asymptotic Error Bounds for SMC with Biased Proposals: Application to Conditional Diffusion Sampling
arXiv:2607. 04780v1 Announce Type: cross Abstract: Sequential Monte Carlo (SMC) methods are a natural tool for post-hoc conditioning of pretrained generative models, but in many applications the mutation kernels used by the particle system are biased approximations of an ideal Feynman--Kac flow.
arXiv Machine Learning
Jun 4
On Forgetting and Stability of Score-based Generative models
arXiv:2601. 21868v2 Announce Type: replace-cross Abstract: Understanding the stability and long-time behavior of generative models is a fundamental problem in modern machine learning.
Hugging Face Trending Papers
Aug 10
Renormalising Generative Models for Active Inference: Foundations, Derivations, and Verification
Active inference offers a unified framework for perception, learning, and action, but scaling discrete active-inference models to rich spatial and temporal domains remains difficult. Renormalising generative models (RGMs) address this challenge by composing discrete generative models across spatial and temporal scales, coarse-graining lower-level states and paths into higher-level causes for objects, events, and action.
arXiv AI
Jul 28
All in One: Generative Modeling as Mean-Field Game Design
arXiv:2607. 23026v1 Announce Type: cross Abstract: Mean-field games (MFGs) offer a unifying lens on continuous-time generative modeling: a cost tuple recovering twelve prominent models---Continuous Normalizing Flows, OT-Flow, Score-based Models, Schr\"{o}dinger Bridges, and more---as special cases of one variational problem.