Gaussian process regression improves diffusion MRI data accuracy and efficiency.
problem Improving accuracy and efficiency of diffusion MRI data, especially for non-uniform and undersampled data.
method Gaussian process regression to estimate diffusion MRI signals at arbitrary locations.
result The method outperforms linear interpolation and allows significant undersampling.
Diffusion models generate private synthetic images with high quality.
problem Generating private synthetic images from sensitive datasets.
method Differentially private fine-tuning of pre-trained diffusion models.
result Improved synthetic data quality and accuracy compared to non-private models.
Generates financial time series with stylized facts using diffusion models.
problem Generating realistic synthetic financial time series with statistical properties like fat tails, volatility clustering, and seasonality.
method Utilizes denoising diffusion probabilistic models (DDPMs) with wavelet transformation to convert and generate financial time series.
result Demonstrates that the proposed approach satisfies stylized financial time series properties.
DiffDenoise preserves fine structures in medical images using conditional diffusion models.
problem Medical image denoising often results in loss of fine structures.
method Conditional diffusion model with stabilized reverse sampling and supervised training.
result DiffDenoise outperforms state-of-the-art methods in medical image denoising.
LightSBB-M improves generative diffusion modeling with lower 2-Wasserstein distances.
problem Improving generative diffusion models using Schrödinger Bridge and Bass methods.
method Optimizes SBB transport plan with dual representation and tunable beta parameter.
result Achieves up to 32% improvement in 2-Wasserstein distance on synthetic datasets.
A new method combines generative and feature-based approaches for unsupervised anomaly detection.
problem Identifying subtle anomalies in test samples compared to a normative distribution.
method A generative cold-diffusion pipeline trained to restore synthetically-corrupted images, combined with a novel synthetic anomaly generation procedure and ensembling restorations.
result Surpasses prior state-of-the-art for unsupervised anomaly detection in three Brain MRI datasets.
Boomerang generates nonidentical images similar to input on image manifolds.
problem Generating nonidentical images similar to input on image manifolds.
method Adding noise to input image, moving closer to latent space, and mapping back through partial reverse diffusion.
result Boomerang generates nonidentical images similar to input on image manifolds.
A new method for generating synthetic data using posterior distribution learning accelerates inference.
problem Generating high-quality synthetic data requires many discretization steps, which is computationally expensive.
method Learning the posterior distribution of clean data samples given noisy versions, using a scoring rule instead of regression loss.
result Consistently outperforms standard diffusion models at few discretization steps.
Measures mode separation in high-dimensional densities via a reversible diffusion process.
problem Quantifying how sharply a distribution fragments into barrier-separated clusters in high dimensions.
method A unique reversible diffusion process with f as stationary distribution, extracting SSA and DA from its autocovariance matrix.
result Empirical autocovariance spectrum and readouts (SSA, DA) quantify mode separation using only samples and pretrained score-based models.
We prove an upper bound on the bottom of the essential spectrum of a diffusion in term of the growth of the volume of X, generalizing a result by R. Brooks.
CSDM integrates compressed sensing into diffusion models for faster data generation.
problem Efficiently generating synthetic data in high-dimensional spaces.
method Integrating compressed sensing into diffusion models (CSDM) to reduce dimensionality and accelerate inference.
result Achieves provably faster convergence and better latent space dimension selection.
DPDMs use DP-SGD to generate private synthetic data.
problem Generating private synthetic data from sensitive datasets.
method Introduced DP-SGD for DMs, investigated DM parameterization and sampling, proposed noise multiplicity.
result Achieved state-of-the-art performance in image generation benchmarks.
New findings on diffusion rates in wind-tree model with rational parameters.
problem Understanding diffusion rates in the wind-tree model with rational parameters.
method Analyzing real numbers in [0,1) as diffusion rates and providing a criterion for Lyapunov spectrum.
result Exhibit an infinite family of wind-tree billiards with the interior of the Lyapunov spectrum being the full square (0,1)^2.
The paper analyzes how synthetic data training degrades diffusion models, providing bounds and characterizing different drift regimes.
problem The degradation of performance in diffusion models trained on synthetic data.
method Theoretical analysis of score-based diffusion models, focusing on the accumulated divergence between generated and target distributions.
result Upper and lower bounds on the accumulated divergence, providing the first lower bound for diffusion models.
New methods create counterfactuals for image regression models.
problem Creating interpretable explanations for regression models in images.
method Two methods using diffusion-based generative models to create counterfactuals.
result Diffusion-based methods produce realistic, semantic, and smooth counterfactuals.
Infinite-dimensional SBDMs improve image generation across multiple resolutions.
problem Efficient image generation at high resolutions and across different levels.
method Developed SBDMs in infinite-dimensional setting, using trace class operators and operator networks.
result Improved efficiency and generalization across resolution levels.
Deep model integrates MRI and DTI for autism severity prediction.
problem Predicting spectrum-level deficits in autism using multimodal brain imaging.
method Generative deep-learning framework combining rs-fMRI and DTI data.
result Hybrid model outperforms existing methods in predicting autism severity.
New method uses diffusion models for Bayesian inverse problems.
problem Solving Bayesian inverse problems with linear-Gaussian models.
method Decoupled Diffusion Sequential Monte Carlo (DDSMC) method.
result Asymptotically exact solution demonstrated on various data types.
Efficiently distills pretrained text-to-image models without real data, improving FID and CLIP scores.
problem Slow iterative refinement process of diffusion-based text-to-image models.
method Guided Score identity Distillation with Long and Short Classifier-Free Guidance.
result Achieves state-of-the-art FID performance with competitive CLIP score.
Improved OOD detection across various shifts using multi-encoder fusion of RDMs.
problem Out-of-distribution detection across multiple types of distribution shifts.
method Statistical identification of encoder sensitivity, EncMin2L fusion, and Tippett minimum combination.
result Achieves AUROC ≥ 0.94 across four shift types, outperforming state-of-the-art detectors.
We identify 'critical windows' in diffusion models where specific features emerge, providing a theoretical framework.
problem Understanding narrow time intervals in diffusion models where specific features emerge.
method Developed a formal framework to study these critical windows, showing provable bounds for certain data types.
result Proved that critical windows can be bounded in terms of measures of separation for data from mixtures of log-concave densities.
A new diffusion model improves cryo-EM structure sampling.
problem Gaussian prior in VAE fails to match approximate posterior in cryo-EM data.
method Train a diffusion model as an expressive, learnable prior in cryoDRGN framework.
result Samples accurately follow the data distribution, not the VAE prior.
New diffusion models handle constrained domains, improving generative tasks.
problem Diffusion models struggle with manifolds defined by inequality constraints.
method Developed two noising processes: logarithmic barrier metric and reflected Brownian motion.
result Demonstrated practical utility on synthetic and real-world tasks.
CTSyn generates high-quality synthetic tabular data.
problem Challenges in generating high-quality synthetic tabular data.
method Diffusion-based generative foundation model with autoencoder and conditional latent diffusion.
result CTSyn outperforms existing table synthesizers on standard benchmarks.
SPI uses synthetic data to improve predictive inference efficiency.
problem Inefficient predictive inference with scarce calibration data.
method Integrates synthetic data to align nonconformity scores and improve coverage guarantees.
result SPI yields substantially tighter and more informative prediction sets.
Introduces MFVDM for high-dimensional data analysis.
problem Non-linear dimensionality reduction of high-dimensional datasets.
method Combines multiple unitary irreducible representations for nonlinear embeddings.
result Achieves better nearest neighbor search and alignment estimation on noisy data.
Unified approach for multimodal data prediction using synthetic data generation.
problem Challenges in integrating heterogeneous data types for accurate predictive performance.
method Generative Distribution Prediction (GDP) framework that uses multimodal synthetic data generation.
result Empirical validation across four tasks demonstrates versatility and effectiveness of GDP.
New AI method generates SDE paths without explicit coefficients.
problem Simulating unknown Markovian SDEs with limited data.
method Uses conditional diffusion models on sample paths.
result Consistently outperforms alternative methods in KL divergence.
This paper proposes a more efficient training method for energy-based models.
problem The computational burden and validity trade-off in Contrastive Divergence training.
method Introducing Diffusion Contrastive Divergence (DCD) to replace Langevin dynamics with diffusion processes.
result The proposed DCDs are more computationally efficient and handle gradient terms better than Contrastive Divergence.
SAMI learns disentangled representations from data.
problem Learning disentangled representations from data.
method Combines diffusion models and VAEs to learn disentangled representations.
result SAMI learns disentangled representations that are interpretable and useful.
PNDMs accelerate DDPMs by treating them as differential equations on manifolds.
problem Accelerate DDPMs while maintaining sample quality.
method Propose pseudo numerical methods (PNDMs) to solve differential equations on manifolds.
result PNDMs generate higher quality images with only 50 steps compared to 1000-step DDIMs (20x speedup).
I2SB learns nonlinear diffusion processes between images.
problem Image restoration tasks, especially with limited structural information.
method Conditional diffusion models, Schrödinger bridge approach.
result I2SB outperforms standard models in various image restoration tasks. Global solutions found for certain reaction-diffusion equations on specific manifolds.
problem Understanding reaction-diffusion equations on various manifolds.
method Analyzing the bottom of the L2 spectrum of −Δ and using time-independent nonlinearities. result Global existence of solutions for certain power nonlinearities on specific manifolds.
Proposes diffusion models using mixed Gaussian priors for better data representation.
problem Improving data representation in diffusion models.
method Structured diffusion models with a mixture of Gaussians as prior.
result Improved model performance compared to classical diffusion models.
New method tackles video inverse problems using image diffusion models.
problem Spatio-temporal degradation in video inverse problems.
method Leverages image diffusion models to treat time dimension as batch dimension, introduces batch-consistent diffusion sampling.
result Achieves state-of-the-art reconstructions for various spatio-temporal degradations.
New nonlocal neural network learns stable dynamics for deeper nonlocal structures.
problem Capturing long-range dependencies in feature space.
method Spectrum analysis on weight matrices, new nonlocal block formulation.
result Stable dynamics in deeper nonlocal structures.
We present two graph-based algorithms for multiclass segmentation of high-dimensional data. The algorithms use a diffuse interface model based on the Ginzburg-Landau functional, related to total variation compressed sensing and image processing. A multiclass extension is introduced using the Gibbs simplex, with the fun…
This paper simplifies diffusion models for high resolution images.
problem Applying diffusion models to high resolution images is challenging.
method Adjust noise schedule, scale specific parts, add dropout, and use downsampling.
result Achieved state-of-the-art image generation performance.
Active learning method for high-dimensional data using diffusion processes.
problem High-dimensional data labeling with limited labels.
method Learning intrinsic data geometries through diffusion processes on graphs, using diffusion distances to parametrize low-dimensional structures.
result The method achieves high-accuracy labelings with only a small number of carefully chosen labels.
Quantum models improve data generation from noisy quantum processors.
problem Creating complex probability distributions from limited data.
method Quantum-noise-driven generative diffusion models.
result Quantum noise can be harnessed to generate more complex distributions efficiently.
Beta diffusion generates bounded data using multiplicative transitions.
problem Generating data within specific ranges.
method Integrates demasking and denoising with scaled and shifted beta distributions.
result KLUBs are more effective for optimizing beta diffusion compared to negative ELBOs.
New method improves image generation for inverse problems using text prompts.
problem Suboptimal performance of existing latent diffusion models for inverse problems.
method Prompt tuning and latent variable projection to optimize text embeddings.
result P2L method outperforms existing methods on various inverse problem tasks.
Residual Prior Diffusion integrates coarse latent priors with diffusion models for better generative tasks.
problem Diffusion models struggle with representing both large-scale and fine-scale details in data distributions.
method Two-stage framework: first a coarse prior model captures large-scale structure, then a diffusion model represents the residual.
result RPD accurately captures fine-scale details while preserving large-scale structure, outperforming standard diffusion models.
Improved image translation using asymmetric gradient guidance.
problem Trade-off between style transformation and content preservation in diffusion models.
method Asymmetric gradient guidance to guide reverse diffusion sampling.
result Our method outperforms state-of-the-art models in image translation tasks.
DEUA detects diffusion-generated images by accounting for different types of uncertainty.
problem Detecting generated images with varying aleatoric and epistemic uncertainty.
method DEUA framework using Laplace approximation for DEU estimation and asymmetric loss function.
result DEUA achieves state-of-the-art performance on large-scale benchmarks.
DreamFusion uses text-to-image diffusion models to create 3D images efficiently.
problem Lack of large-scale 3D datasets and efficient architectures for 3D synthesis.
method Adapting a 2D diffusion model to 3D synthesis using a loss based on probability density distillation.
result A 3D model can be optimized from a 2D diffusion model, allowing for text-to-3D synthesis.
Zero-shot contrastive loss improves text-guided image style transfer without extra training.
problem Stochastic nature of diffusion models leads to trade-offs between style transformation and content preservation.
method Proposes a zero-shot contrastive loss for diffusion models that doesn't require additional fine-tuning or auxiliary networks.
result Method outperforms existing methods while preserving content and requiring no additional training.
A new pyramidal diffusion model speeds up image generation.
problem Training and evaluating diffusion models are time-consuming.
method Introduces a pyramidal diffusion model with a single score function.
result Generates high-resolution images from low-resolution starting points efficiently.