CDM migrates distribution matching distillation to continuous time via dynamic random-length schedules and active off-trajectory latent alignment, yielding competitive few-step image fidelity on SD3 and Longcat-Image.
hub
Denoising diffusion implicit models
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
Introduces a marginal-alignment regularizer for reflow distillation of diffusion models that aligns endpoint marginals, supported by a telescoping TV bound and benchmark experiments.
A control-theoretic linear program yields value-driven transport policies for generative modeling with straight paths and simulation-free training.
Introduces MO-ARM framework for training order-agnostic autoregressive models directly on incomplete data, showing implicit MCAR imputation in standard training and outperforming baselines on benchmarks.
Prompts can be split into separate roles for sampling design and recovery modeling in generative compressed sensing, with stable recovery bounds for matched prompts and an explicit penalty for mismatch, validated on Stable Diffusion.
VDC amortizes vine copula construction by reusing a single trained denoising model across edges plus IPFP projection, yielding competitive density and mutual information estimates with faster high-dimensional fitting.
Derives exact guidance transition rates for discrete flow matching models that require only one model evaluation per sampling step and unify prior approximation-based methods.
In the Gaussian setting the Wasserstein error of score-matching-plus-diffusion sampling equals a kernel norm of the data power spectrum whose kernel is determined by the four error sources and the algorithm parameters.
Patch-PODiff-ViT defines a structured latent space via patchwise POD for efficient diffusion-based super-resolution and direct analytic uncertainty quantification across scientific and natural images.
GORMPO uses generative models for density-based regularization in model-based offline RL, outperforming baselines by 17% on a medical dataset while providing theoretical guarantees under mild assumptions.
GOAL uses conditioned diffusion on relational graphs with typed edges to produce feasible multi-objective solutions for scheduling problems, reporting 100% feasibility and sub-0.2% MAPE on FSP, JSP, and FJSP up to 20 jobs.
LAMP adds a lagged temporal correction derived from second-order discretization to diffusion posterior samplers, yielding consistent gains over DiffPIR and DDRM on imaging tasks via a bias-variance trade-off.
PGID restores watermark detection in diffusion models by using progressive inversion-denoising cycles to correct latents displaced by removal or forgery attacks.
OPAD enables reliable high-quality personalization of one-step diffusion models via multi-step teacher distillation combined with adversarial alignment losses.
NPN introduces a neural-network-based regularization that promotes reconstructions lying in a low-dimensional projection of the sensing operator's null-space, with claimed theoretical guarantees and improved empirical performance across compressive sensing, deblurring, super-resolution, CT, and MRI.
Derives closed-form optimal loss for unified diffusion models, provides variance-controlled estimators, and shows improved diagnosis, training schedules, and power-law scaling after subtracting the optimal value.
Latent Wavelet Diffusion uses wavelet energy map masking and a scale-consistent VAE to improve detail fidelity in 2K-4K image generation without extra inference overhead.
A confidence-guided diffusion framework generates synthetic Bangla compound characters that, when filtered and added to training data, raise classifier accuracy to 89.2% on the AIBangla dataset.
A tutorial that unifies diffusion probabilistic models, score-based generative modeling, and SDE methods by deriving forward and reverse dynamics from a shared Gaussian noising process.
citing papers explorer
-
Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
CDM migrates distribution matching distillation to continuous time via dynamic random-length schedules and active off-trajectory latent alignment, yielding competitive few-step image fidelity on SD3 and Longcat-Image.
-
Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment
Introduces a marginal-alignment regularizer for reflow distillation of diffusion models that aligns endpoint marginals, supported by a telescoping TV bound and benchmark experiments.
-
Generative Modeling by Value-Driven Transport
A control-theoretic linear program yields value-driven transport policies for generative modeling with straight paths and simulation-free training.
-
Order-Agnostic Autoregressive Modelling with Missing Data
Introduces MO-ARM framework for training order-agnostic autoregressive models directly on incomplete data, showing implicit MCAR imputation in standard training and outperforming baselines on benchmarks.
-
Active Learning for Conditional Generative Compressed Sensing
Prompts can be split into separate roles for sampling design and recovery modeling in generative compressed sensing, with stable recovery bounds for matched prompts and an explicit penalty for mismatch, validated on Stable Diffusion.
-
Amortized Vine Copulas for High-Dimensional Density and Information Estimation
VDC amortizes vine copula construction by reusing a single trained denoising model across edges plus IPFP projection, yielding competitive density and mutual information estimates with faster high-dimensional fitting.
-
Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching
Derives exact guidance transition rates for discrete flow matching models that require only one model evaluation per sampling step and unify prior approximation-based methods.
-
From Score Matching to Diffusion: A Fine-Grained Error Analysis in the Gaussian Setting
In the Gaussian setting the Wasserstein error of score-matching-plus-diffusion sampling equals a kernel norm of the data power spectrum whose kernel is determined by the four error sources and the algorithm parameters.
-
Patch-PODiff-ViT: Structured Latent Diffusion with Patchwise POD for Super-Resolution and Uncertainty Quantification
Patch-PODiff-ViT defines a structured latent space via patchwise POD for efficient diffusion-based super-resolution and direct analytic uncertainty quantification across scientific and natural images.
-
Generative OOD-regularized Model-based Policy Optimization
GORMPO uses generative models for density-based regularization in model-based offline RL, outperforming baselines by 17% on a medical dataset while providing theoretical guarantees under mild assumptions.
-
GOAL: Graph-based Objective-Aligned Diffusion Solvers for Dynamic Multi-Objective Optimization
GOAL uses conditioned diffusion on relational graphs with typed edges to produce feasible multi-objective solutions for scheduling problems, reporting 100% feasibility and sub-0.2% MAPE on FSP, JSP, and FJSP up to 20 jobs.
-
Improving Diffusion Posterior Samplers with Lagged Temporal Corrections for Image Restoration
LAMP adds a lagged temporal correction derived from second-order discretization to diffusion posterior samplers, yielding consistent gains over DiffPIR and DDRM on imaging tasks via a bias-variance trade-off.
-
PGID: Progressive Guided Inversion and Denoising for Robust Watermark Detection
PGID restores watermark detection in diffusion models by using progressive inversion-denoising cycles to correct latents displaced by removal or forgery attacks.
-
Adversarial Concept Distillation for One-Step Diffusion Personalization
OPAD enables reliable high-quality personalization of one-step diffusion models via multi-step teacher distillation combined with adversarial alignment losses.
-
NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems
NPN introduces a neural-network-based regularization that promotes reconstructions lying in a low-dimensional projection of the sensing operator's null-space, with claimed theoretical guarantees and improved empirical performance across compressive sensing, deblurring, super-resolution, CT, and MRI.
-
Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value
Derives closed-form optimal loss for unified diffusion models, provides variance-controlled estimators, and shows improved diagnosis, training schedules, and power-law scaling after subtracting the optimal value.
-
Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesis
Latent Wavelet Diffusion uses wavelet energy map masking and a scale-consistent VAE to improve detail fidelity in 2K-4K image generation without extra inference overhead.
-
Confidence-Guided Diffusion Augmentation for Enhanced Bangla Compound Character Recognition
A confidence-guided diffusion framework generates synthetic Bangla compound characters that, when filtered and added to training data, raise classifier accuracy to 89.2% on the AIBangla dataset.
-
A Tutorial on Diffusion Theory: From Differential Equations to Diffusion Models
A tutorial that unifies diffusion probabilistic models, score-based generative modeling, and SDE methods by deriving forward and reverse dynamics from a shared Gaussian noising process.