mailitics

Tag: diffusion

  • Drift Estimation for Stochastic Differential Equations with Denoising Diffusion Models

    Drift Estimation for Stochastic Differential Equations with Denoising Diffusion Models arXiv:2602.17830v1 Announce Type: new Abstract: We study the estimation of time-homogeneous drift functions in multivariate stochastic differential equations with known diffusion coefficient, from multiple trajectories observed at high frequency over a fixed time horizon. We formulate drift estimation as a denoising problem conditional on previous…

  • Quantifying Epistemic Uncertainty in Diffusion Models

    Quantifying Epistemic Uncertainty in Diffusion Models arXiv:2602.09170v1 Announce Type: new Abstract: To ensure high quality outputs, it is important to quantify the epistemic uncertainty of diffusion models.Existing methods are often unreliable because they mix epistemic and aleatoric uncertainty. We introduce a method based on Fisher information that explicitly isolates epistemic variance, producing more reliable plausibility…

  • Fast and Robust Likelihood-Guided Diffusion Posterior Sampling with Amortized Variational Inference

    Fast and Robust Likelihood-Guided Diffusion Posterior Sampling with Amortized Variational Inference arXiv:2602.07102v1 Announce Type: new Abstract: Zero-shot diffusion posterior sampling offers a flexible framework for inverse problems by accommodating arbitrary degradation operators at test time, but incurs high computational cost due to repeated likelihood-guided updates. In contrast, previous amortized diffusion approaches enable fast inference by…

  • Training-Free Self-Correction for Multimodal Masked Diffusion Models

    Training-Free Self-Correction for Multimodal Masked Diffusion Models arXiv:2602.02927v1 Announce Type: new Abstract: Masked diffusion models have emerged as a powerful framework for text and multimodal generation. However, their sampling procedure updates multiple tokens simultaneously and treats generated tokens as immutable, which may lead to error accumulation when early mistakes cannot be revised. In this work,…

  • Alignment of Diffusion Model and Flow Matching for Text-to-Image Generation

    Alignment of Diffusion Model and Flow Matching for Text-to-Image Generation arXiv:2602.00413v1 Announce Type: new Abstract: Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-trained generative models to maximize a given reward function, these approaches require extensive computational resources and may not generalize…

  • Towards Latent Diffusion Suitable For Text

    Towards Latent Diffusion Suitable For Text arXiv:2601.16220v1 Announce Type: cross Abstract: Language diffusion models aim to improve sampling speed and coherence over autoregressive LLMs. We introduce Neural Flow Diffusion Models for language generation, an extension of NFDM that enables the straightforward application of continuous diffusion models to discrete state spaces. NFDM learns a multivariate forward…

  • Inference-Time Alignment for Diffusion Models via Doob’s Matching

    Inference-Time Alignment for Diffusion Models via Doob’s Matching arXiv:2601.06514v1 Announce Type: new Abstract: Inference-time alignment for diffusion models aims to adapt a pre-trained diffusion model toward a target distribution without retraining the base score network, thereby preserving the generative capacity of the base model while enforcing desired properties at the inference time. A central mechanism…

  • Residual Prior Diffusion: A Probabilistic Framework Integrating Coarse Latent Priors with Diffusion Models

    Residual Prior Diffusion: A Probabilistic Framework Integrating Coarse Latent Priors with Diffusion Models arXiv:2512.21593v1 Announce Type: new Abstract: Diffusion models have become a central tool in deep generative modeling, but standard formulations rely on a single network and a single diffusion schedule to transform a simple prior, typically a standard normal distribution, into the target…

  • Diffusion Models in Simulation-Based Inference: A Tutorial Review

    Diffusion Models in Simulation-Based Inference: A Tutorial Review arXiv:2512.20685v1 Announce Type: new Abstract: Diffusion models have recently emerged as powerful learners for simulation-based inference (SBI), enabling fast and accurate estimation of latent parameters from simulated and real data. Their score-based formulation offers a flexible way to learn conditional or joint distributions over parameters and observations,…

  • Diffusion differentiable resampling

    Diffusion differentiable resampling arXiv:2512.10401v1 Announce Type: new Abstract: This paper is concerned with differentiable resampling in the context of sequential Monte Carlo (e.g., particle filtering). We propose a new informative resampling method that is instantly pathwise differentiable, based on an ensemble score diffusion model. We prove that our diffusion resampling method provides a consistent estimate…

  • One-Step Diffusion Samplers via Self-Distillation and Deterministic Flow

    One-Step Diffusion Samplers via Self-Distillation and Deterministic Flow arXiv:2512.05251v1 Announce Type: new Abstract: Sampling from unnormalized target distributions is a fundamental yet challenging task in machine learning and statistics. Existing sampling algorithms typically require many iterative steps to produce high-quality samples, leading to high computational costs. We introduce one-step diffusion samplers which learn a step-conditioned…

  • Towards a unified framework for guided diffusion models

    Towards a unified framework for guided diffusion models arXiv:2512.04985v1 Announce Type: new Abstract: Guided or controlled data generation with diffusion modelsblfootnote{Partial preliminary results of this work appeared in International Conference on Machine Learning 2025 citep{li2025provable}.} has become a cornerstone of modern generative modeling. Despite substantial advances in diffusion model theory, the theoretical understanding of guided…

  • Diffusion-Inversion-Net (DIN): An End-to-End Direct Probabilistic Framework for Characterizing Hydraulic Conductivities and Quantifying Uncertainty

    Diffusion-Inversion-Net (DIN): An End-to-End Direct Probabilistic Framework for Characterizing Hydraulic Conductivities and Quantifying Uncertainty arXiv:2511.16926v1 Announce Type: cross Abstract: We propose the Diffusion-Inversion-Net (DIN) framework for inverse modeling of groundwater flow and solute transport processes. DIN utilizes an offline-trained Denoising Diffusion Probabilistic Model (DDPM) as a powerful prior leaner, which flexibly incorporates sparse, multi-source observational…

  • DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing

    DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing arXiv:2511.17038v1 Announce Type: cross Abstract: From a Bayesian perspective, score-based diffusion solves inverse problems through joint inference, embedding the likelihood with the prior to guide the sampling process. However, this formulation fails to explain its practical behavior: the prior offers limited guidance, while reconstruction is largely…

  • Drift Estimation for Diffusion Processes Using Neural Networks Based on Discretely Observed Independent Paths

    Drift Estimation for Diffusion Processes Using Neural Networks Based on Discretely Observed Independent Paths arXiv:2511.11161v1 Announce Type: new Abstract: This paper addresses the nonparametric estimation of the drift function over a compact domain for a time-homogeneous diffusion process, based on high-frequency discrete observations from $N$ independent trajectories. We propose a neural network-based estimator and derive…

  • Provable Separations between Memorization and Generalization in Diffusion Models

    Provable Separations between Memorization and Generalization in Diffusion Models arXiv:2511.03202v1 Announce Type: new Abstract: Diffusion models have achieved remarkable success across diverse domains, but they remain vulnerable to memorization — reproducing training data rather than generating novel outputs. This not only limits their creative potential but also raises concerns about privacy and safety. While empirical…

  • Compositional Generation for Long-Horizon Coupled PDEs

    Compositional Generation for Long-Horizon Coupled PDEs arXiv:2510.20141v1 Announce Type: new Abstract: Simulating coupled PDE systems is computationally intensive, and prior efforts have largely focused on training surrogates on the joint (coupled) data, which requires a large amount of data. In the paper, we study compositional diffusion approaches where diffusion models are only trained on the…

  • Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling

    Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling arXiv:2510.01329v1 Announce Type: new Abstract: Standard discrete diffusion models treat all unobserved states identically by mapping them to an absorbing [MASK] token. This creates an ‘information void’ where semantic information that could be inferred from unmasked tokens is lost between denoising steps. We introduce Continuously Augmented…

  • Diffusion Generative Models Meet Compressed Sensing, with Applications to Image Data and Financial Time Series

    Diffusion Generative Models Meet Compressed Sensing, with Applications to Image Data and Financial Time Series arXiv:2509.03898v1 Announce Type: new Abstract: This paper develops dimension reduction techniques for accelerating diffusion model inference in the context of synthetic data generation. The idea is to integrate compressed sensing into diffusion models: (i) compress the data into a latent…

  • Partial Functional Dynamic Backdoor Diffusion-based Causal Model

    Partial Functional Dynamic Backdoor Diffusion-based Causal Model arXiv:2509.00472v1 Announce Type: new Abstract: We introduce a Partial Functional Dynamic Backdoor Diffusion-based Causal Model (PFD-BDCM), specifically designed for causal inference in the presence of unmeasured confounders with spatial heterogeneity and temporal dependency. The proposed PFD-BDCM framework addresses the restrictions of the existing approaches by uniquely integrating models…

  • The Information Dynamics of Generative Diffusion

    The Information Dynamics of Generative Diffusion arXiv:2508.19897v1 Announce Type: new Abstract: Generative diffusion models have emerged as a powerful class of models in machine learning, yet a unified theoretical understanding of their operation is still developing. This perspective paper provides an integrated perspective on generative diffusion by connecting their dynamic, information-theoretic, and thermodynamic properties under…

  • Non-asymptotic convergence bound of conditional diffusion models

    Non-asymptotic convergence bound of conditional diffusion models arXiv:2508.10944v1 Announce Type: new Abstract: Learning and generating various types of data based on conditional diffusion models has been a research hotspot in recent years. Although conditional diffusion models have made considerable progress in improving acceleration algorithms and enhancing generation quality, the lack of non-asymptotic properties has hindered…

  • Likelihood Matching for Diffusion Models

    Likelihood Matching for Diffusion Models arXiv:2508.03636v1 Announce Type: new Abstract: We propose a Likelihood Matching approach for training diffusion models by first establishing an equivalence between the likelihood of the target data distribution and a likelihood along the sample path of the reverse diffusion. To efficiently compute the reverse sample likelihood, a quasi-likelihood is considered…

  • Diffusion Models for Time Series Forecasting: A Survey

    Diffusion Models for Time Series Forecasting: A Survey arXiv:2507.14507v1 Announce Type: new Abstract: Diffusion models, initially developed for image synthesis, demonstrate remarkable generative capabilities. Recently, their application has expanded to time series forecasting (TSF), yielding promising results. In this survey, we firstly introduce the standard diffusion models and their prevalent variants, explaining their adaptation to…

  • TADA: Improved Diffusion Sampling with Training-free Augmented Dynamics

    TADA: Improved Diffusion Sampling with Training-free Augmented Dynamics arXiv:2506.21757v1 Announce Type: new Abstract: Diffusion models have demonstrated exceptional capabilities in generating high-fidelity images but typically suffer from inefficient sampling. Many solver designs and noise scheduling strategies have been proposed to dramatically improve sampling speeds. In this paper, we introduce a new sampling method that is…

  • Diffusion-Based Hypothesis Testing and Change-Point Detection

    Diffusion-Based Hypothesis Testing and Change-Point Detection arXiv:2506.16089v1 Announce Type: new Abstract: Score-based methods have recently seen increasing popularity in modeling and generation. Methods have been constructed to perform hypothesis testing and change-point detection with score functions, but these methods are in general not as powerful as their likelihood-based peers. Recent works consider generalizing the score-based…

  • Measuring Semantic Information Production in Generative Diffusion Models

    Measuring Semantic Information Production in Generative Diffusion Models arXiv:2506.10433v1 Announce Type: new Abstract: It is well known that semantic and structural features of the generated images emerge at different times during the reverse dynamics of diffusion, a phenomenon that has been connected to physical phase transitions in magnets and other materials. In this paper, we…

  • Enabling Probabilistic Learning on Manifolds through Double Diffusion Maps

    Enabling Probabilistic Learning on Manifolds through Double Diffusion Maps arXiv:2506.02254v1 Announce Type: new Abstract: We present a generative learning framework for probabilistic sampling based on an extension of the Probabilistic Learning on Manifolds (PLoM) approach, which is designed to generate statistically consistent realizations of a random vector in a finite-dimensional Euclidean space, informed by a…

  • Diffusion Models, Explained Simply

    Diffusion Models, Explained Simply Introduction Generative AI is one of the most popular terms we hear today. Recently, there has been a surge in generative AI applications involving text, image, audio, and video generation. When it comes to image creation, Diffusion models have emerged as a state-of-the-art technique for content generation. Although they were first introduced…

  • Provable Efficiency of Guidance in Diffusion Models for General Data Distribution

    Provable Efficiency of Guidance in Diffusion Models for General Data Distribution arXiv:2505.01382v1 Announce Type: new Abstract: Diffusion models have emerged as a powerful framework for generative modeling, with guidance techniques playing a crucial role in enhancing sample quality. Despite their empirical success, a comprehensive theoretical understanding of the guidance effect remains limited. Existing studies only…

  • AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse

    AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse arXiv:2504.10540v1 Announce Type: new Abstract: Diffusion models have demonstrated remarkable success in generative tasks, yet their iterative denoising process results in slow inference, limiting their practicality. While existing acceleration methods exploit the well-known U-shaped similarity pattern between adjacent steps through caching mechanisms, they lack…

  • The Art of Noise

    The Art of Noise Introduction In my last several articles I talked about generative deep learning algorithms, which mostly are related to text generation tasks. So, I think it would be interesting to switch to generative algorithms for image generation now. We knew that nowadays there have been plenty of deep learning models specialized for…

  • Non-asymptotic Analysis of Diffusion Annealed Langevin Monte Carlo for Generative Modelling

    Non-asymptotic Analysis of Diffusion Annealed Langevin Monte Carlo for Generative Modelling arXiv:2502.09306v1 Announce Type: new Abstract: We investigate the theoretical properties of general diffusion (interpolation) paths and their Langevin Monte Carlo implementation, referred to as diffusion annealed Langevin Monte Carlo (DALMC), under weak conditions on the data distribution. Specifically, we analyse and provide non-asymptotic error…

  • Six Ways to Control Style and Content in Diffusion Models

    Six Ways to Control Style and Content in Diffusion Models Stable Diffusion 1.5/2.0/2.1/XL 1.0, DALL-E, Imagen… In the past years, Diffusion Models have showcased stunning quality in image generation. However, while producing great quality on generic concepts, these struggle to generate high quality for more specialised queries, for example generating images in a specific style,…

  • A Visual Guide to How Diffusion Models Work

    A Visual Guide to How Diffusion Models Work This article is aimed at those who want to understand exactly how Diffusion Models work, with no prior knowledge expected. I’ve tried to use illustrations wherever possible to provide visual intuitions on each part of these models. I’ve kept mathematical notation and equations to a minimum, and where…

  • Variational Schr”odinger Momentum Diffusion

    Variational Schr”odinger Momentum Diffusion arXiv:2501.16675v1 Announce Type: new Abstract: The momentum Schr”odinger Bridge (mSB) has emerged as a leading method for accelerating generative diffusion processes and reducing transport costs. However, the lack of simulation-free properties inevitably results in high training costs and affects scalability. To obtain a trade-off between transport properties and scalability, we introduce…

  • Concentration of Measure for Distributions Generated via Diffusion Models

    Concentration of Measure for Distributions Generated via Diffusion Models arXiv:2501.07741v1 Announce Type: new Abstract: We show via a combination of mathematical arguments and empirical evidence that data distributions sampled from diffusion models satisfy a Concentration of Measure Property saying that any Lipschitz $1$-dimensional projection of a random vector is not too far from its mean…

  • Generative Modeling with Diffusion

    Generative Modeling with Diffusion arXiv:2412.10948v1 Announce Type: new Abstract: We introduce the diffusion model as a method to generate new samples. Generative models have been recently adopted for tasks such as art generation (Stable Diffusion, Dall-E) and text generation (ChatGPT). Diffusion models in particular apply noise to sample data and then “reverse” this noising process…

  • Score-Optimal Diffusion Schedules

    Score-Optimal Diffusion Schedules arXiv:2412.07877v1 Announce Type: new Abstract: Denoising diffusion models (DDMs) offer a flexible framework for sampling from high dimensional data distributions. DDMs generate a path of probability distributions interpolating between a reference Gaussian distribution and a data distribution by incrementally injecting noise into the data. To numerically simulate the sampling process, a discretisation…

  • Sequential Controlled Langevin Diffusions

    Sequential Controlled Langevin Diffusions arXiv:2412.07081v1 Announce Type: new Abstract: An effective approach for sampling from unnormalized densities is based on the idea of gradually transporting samples from an easy prior to the complicated target distribution. Two popular methods are (1) Sequential Monte Carlo (SMC), where the transport is performed through successive annealed densities via prescribed…

  • How well behaved is finite dimensional Diffusion Maps?

    How well behaved is finite dimensional Diffusion Maps? arXiv:2412.03992v1 Announce Type: new Abstract: Under a set of assumptions on a family of submanifolds $subset {mathbb R}^D$, we derive a series of geometric properties that remain valid after finite-dimensional and almost isometric Diffusion Maps (DM), including almost uniform density, finite polynomial approximation and local reach. Leveraging…

  • Generalized Diffusion Model with Adjusted Offset Noise

    Generalized Diffusion Model with Adjusted Offset Noise arXiv:2412.03134v1 Announce Type: new Abstract: Diffusion models have become fundamental tools for modeling data distributions in machine learning and have applications in image generation, drug discovery, and audio synthesis. Despite their success, these models face challenges when generating data with extreme brightness values, as evidenced by limitations in…