Proves dimension-uniform KL bounds for exponential-integrator discretization of preconditioned ALD on Gaussian mixtures under spectral summability, showing EM stability restrictions are scheme-dependent rather than intrinsic.
Generative modeling by estimating gradients of the data distribution.Advances in Neural Information Processing Systems, 32
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
GG-PA composes diffusion priors with physical context via a derived Gibbs sampler that is asymptotically exact as diffusion time approaches zero and exact at finite times for quadratic interactions.
SOM is an actor-critic algorithm that constructs the target velocity field for one-step MeanFlow policies directly from the Q-function via score estimation and probability flow ODE, achieving claimed SOTA on locomotion tasks with reduced training and inference time.
Drifting with Gaussian kernels exactly matches score-matching on smoothed distributions via Tweedie's formula, while Laplace kernels approximate this closely in high dimensions.
Aligning the DDIM forward diffusion process with flow-matching manifold evolution enables high-quality generation without time conditioning, and class-conditional synthesis is possible with an unconditional denoiser by using separate time spaces per class.
citing papers explorer
-
Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian Mixtures
Proves dimension-uniform KL bounds for exponential-integrator discretization of preconditioned ALD on Gaussian mixtures under spectral summability, showing EM stability restrictions are scheme-dependent rather than intrinsic.
-
Composing diffusion priors with explicit physical context via generative Gibbs sampling
GG-PA composes diffusion priors with physical context via a derived Gibbs sampler that is asymptotically exact as diffusion time approaches zero and exact at finite times for quadratic interactions.
-
Score-Based One-step MeanFlow Policy Optimization
SOM is an actor-critic algorithm that constructs the target velocity field for one-step MeanFlow policies directly from the Q-function via score estimation and probability flow ODE, achieving claimed SOTA on locomotion tasks with reduced training and inference time.
-
A Unified View of Score-Based and Drifting Models
Drifting with Gaussian kernels exactly matches score-matching on smoothed distributions via Tweedie's formula, while Laplace kernels approximate this closely in high dimensions.
-
Exploring Time Conditioning in Diffusion Generative Models from Disjoint Noisy Data Manifolds
Aligning the DDIM forward diffusion process with flow-matching manifold evolution enables high-quality generation without time conditioning, and class-conditional synthesis is possible with an unconditional denoiser by using separate time spaces per class.