Related papers: RNE: a plug-and-play framework for diffusion density estimation and inference-time control

Related papers

SlimDiffSR: Toward Lightweight and Efficient Remote Sensing Image Super-Resolution via Diffusion Model Distillation [10.518150741228862]
SlimDiffSR is a lightweight and efficient diffusion-based framework for real-world remote sensing image super-resolution.<n>It attains up to $200times$ inference acceleration and a $20times$ reduction in model parameters compared with multi-step diffusion models.
arXiv Detail & Related papers (2026-05-04T03:54:54Z)
Causal Autoregressive Diffusion Language Model [70.7353007255797]
CARD reformulates the diffusion process within a strictly causal attention mask, enabling dense, per-token supervision in a single forward pass.<n>Our results demonstrate that CARD achieves ARM-level data efficiency while unlocking the latency benefits of parallel generation.
arXiv Detail & Related papers (2026-01-29T17:38:29Z)
Information Theoretic Learning for Diffusion Models with Warm Start [8.455757095201314]
We derive a tighter likelihood bound for noise driven models to improve the accuracy and efficiency of maximum likelihood learning.<n>Our key insight extends the classical KL divergence Fisher information relationship to arbitrary noise perturbations.<n>Treating the diffusion process as a Gaussian channel, we show that the proposed objective upper bounds the negative log-likelihood (NLL)
arXiv Detail & Related papers (2025-10-23T18:00:59Z)
Blind-Spot Guided Diffusion for Self-supervised Real-World Denoising [55.099717395320276]
Blind-Spot Guided Diffusion is a novel self-supervised framework for real-world image denoising.<n>Our approach addresses two major challenges: the limitations of blind-spot networks (BSNs) and the difficulty of adapting diffusion models to self-supervised denoising.
arXiv Detail & Related papers (2025-09-19T15:35:07Z)
Latent Diffusion Model Based Denoising Receiver for 6G Semantic Communication: From Stochastic Differential Theory to Application [55.42071552739813]
A novel semantic communication framework empowered by generative artificial intelligence (GAI) is proposed.<n>A theoretical foundation is established based on differential equations (SDEs)<n>A closed-form analytical relationship between the signal-to-noise ratio (SNR) and the denoising timestep is derived.<n>To address the distribution mismatch between the received signal and the DM's training data, a mathematically principled scaling mechanism is introduced.
arXiv Detail & Related papers (2025-06-06T03:20:32Z)
Consistent World Models via Foresight Diffusion [56.45012929930605]
We argue that a key bottleneck in learning consistent diffusion-based world models lies in the suboptimal predictive ability.<n>We propose Foresight Diffusion (ForeDiff), a diffusion-based world modeling framework that enhances consistency by decoupling condition understanding from target denoising.
arXiv Detail & Related papers (2025-05-22T10:01:59Z)
Dequantified Diffusion-Schr{ö}dinger Bridge for Density Ratio Estimation [13.986781622423885]
We design a unified framework for robust, stable and efficient density ratio estimation.<n>We propose the dequantified diffusion bridge interpolant (DDBI), which expands support coverage and stabilizes time scores.<n>Building on DDBI, the proposed dequantified Schr"odinger bridge interpolant (D SBI) incorporates optimal transport to solve the Schr"odinger bridge problem.
arXiv Detail & Related papers (2025-05-08T08:12:16Z)
Generative Latent Neural PDE Solver using Flow Matching [8.397730500554047]
We propose a latent diffusion model for PDE simulation that embeds the PDE state in a lower-dimensional latent space.<n>Our framework uses an autoencoder to map different types of meshes onto a unified structured latent grid, capturing complex geometries.<n> Numerical experiments show that the proposed model outperforms several deterministic baselines in both accuracy and long-term stability.
arXiv Detail & Related papers (2025-03-28T16:44:28Z)
Efficient Diffusion Training through Parallelization with Truncated Karhunen-Loève Expansion [5.770347328961063]
Diffusion denoising models suffer from slow convergence during training.<n>We propose a novel forward-time process for training and sampling.<n>Our method significantly outperforms baseline diffusion models.
arXiv Detail & Related papers (2025-03-22T05:34:02Z)
Deterministic Fokker-Planck Transport -- With Applications to Sampling, Variational Inference, Kernel Mean Embeddings & Sequential Monte Carlo [0.0]
We reformulate the Fokker-Planck equation as a continuity equation, which naturally suggests using the associated velocity field in particle flow methods. While the resulting probability flow ODE offers appealing properties, it relies on evaluating the current probability density, which is intractable in most practical applications. We uncover opportunities to turn these limitations into advantages in contexts such as variational inference, kernel mean embeddings, and sequential Monte Carlo.
arXiv Detail & Related papers (2024-10-11T13:06:36Z)
Kinetic Interacting Particle Langevin Monte Carlo [0.0]
This paper introduces and analyses interacting underdamped Langevin algorithms, for statistical inference in latent variable models. We propose a diffusion process that evolves jointly in the space of parameters and latent variables. We provide two explicit discretisations of this diffusion as practical algorithms to estimate parameters of statistical models.
arXiv Detail & Related papers (2024-07-08T09:52:46Z)
Scalable Continuous-time Diffusion Framework for Network Inference and Influence Estimation [27.561806717195054]
In this paper, we view the diffusion process as a continuous-time dynamical system, based on which we establish a continuous-time diffusion model. We then instantiate the model to a scalable and effective framework (FIM) to approximate the diffusion propagation from available cascades. To achieve the desired scalability for influence estimation, we devise an advanced sampling technique and significantly boost the efficiency.
arXiv Detail & Related papers (2024-03-05T11:21:18Z)
Observation-Guided Diffusion Probabilistic Models [41.749374023639156]
We propose a novel diffusion-based image generation method called the observation-guided diffusion probabilistic model (OGDM) Our approach reestablishes the training objective by integrating the guidance of the observation process with the Markov chain. We demonstrate the effectiveness of our training algorithm using diverse inference techniques on strong diffusion model baselines.
arXiv Detail & Related papers (2023-10-06T06:29:06Z)
Semi-Implicit Denoising Diffusion Models (SIDDMs) [50.30163684539586]
Existing models such as Denoising Diffusion Probabilistic Models (DDPM) deliver high-quality, diverse samples but are slowed by an inherently high number of iterative steps. We introduce a novel approach that tackles the problem by matching implicit and explicit factors. We demonstrate that our proposed method obtains comparable generative performance to diffusion-based models and vastly superior results to models with a small number of sampling steps.
arXiv Detail & Related papers (2023-06-21T18:49:22Z)
Low-Light Image Enhancement with Wavelet-based Diffusion Models [50.632343822790006]
Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration. We propose a robust and efficient Diffusion-based Low-Light image enhancement approach, dubbed DiffLL.
arXiv Detail & Related papers (2023-06-01T03:08:28Z)
Diffusion Models are Minimax Optimal Distribution Estimators [49.47503258639454]
We provide the first rigorous analysis on approximation and generalization abilities of diffusion modeling. We show that when the true density function belongs to the Besov space and the empirical score matching loss is properly minimized, the generated data distribution achieves the nearly minimax optimal estimation rates.
arXiv Detail & Related papers (2023-03-03T11:31:55Z)
Diffusion-GAN: Training GANs with Diffusion [135.24433011977874]
Generative adversarial networks (GANs) are challenging to train stably. We propose Diffusion-GAN, a novel GAN framework that leverages a forward diffusion chain to generate instance noise. We show that Diffusion-GAN can produce more realistic images with higher stability and data efficiency than state-of-the-art GANs.
arXiv Detail & Related papers (2022-06-05T20:45:01Z)
Robust Learning via Ensemble Density Propagation in Deep Neural Networks [6.0122901245834015]
We formulate the problem of density propagation through layers of a deep neural network (DNN) and solve it using an Ensemble Density propagation scheme. Experiments using MNIST and CIFAR-10 datasets show a significant improvement in the robustness of the trained models to random noise and adversarial attacks.
arXiv Detail & Related papers (2021-11-10T21:26:08Z)
Deep Data Density Estimation through Donsker-Varadhan Representation [5.276937617129594]
We present a simple yet effective method for estimating the data density using a deep neural network and the Donsker-Varadhan variational lower bound on the KL divergence. We show that the optimal critic function associated with the Donsker-Varadhan representation on the divergence between the data and the uniform distribution can estimate the data density.
arXiv Detail & Related papers (2021-04-14T03:38:32Z)
Probabilistic electric load forecasting through Bayesian Mixture Density Networks [70.50488907591463]
Probabilistic load forecasting (PLF) is a key component in the extended tool-chain required for efficient management of smart energy grids. We propose a novel PLF approach, framed on Bayesian Mixture Density Networks. To achieve reliable and computationally scalable estimators of the posterior distributions, both Mean Field variational inference and deep ensembles are integrated.
arXiv Detail & Related papers (2020-12-23T16:21:34Z)
Imitation with Neural Density Models [98.34503611309256]
We propose a new framework for Imitation Learning (IL) via density estimation of the expert's occupancy measure followed by Imitation Occupancy Entropy Reinforcement Learning (RL) using the density as a reward. Our approach maximizes a non-adversarial model-free RL objective that provably lower bounds reverse Kullback-Leibler divergence between occupancy measures of the expert and imitator.
arXiv Detail & Related papers (2020-10-19T19:38:36Z)
Network Diffusions via Neural Mean-Field Dynamics [52.091487866968286]
We propose a novel learning framework for inference and estimation problems of diffusion on networks. Our framework is derived from the Mori-Zwanzig formalism to obtain an exact evolution of the node infection probabilities. Our approach is versatile and robust to variations of the underlying diffusion network models.
arXiv Detail & Related papers (2020-06-16T18:45:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.