Search: diffusion models

More than 1,000 papers match: here are the 1,000 most recent, ranked by relevance.

• Data assimilation for subsurface flow using latent diffusion model parameterization: performance of ensemble-Kalman and Monte Carlo techniques

  Guido Di Federico, Wenchao Teng, Louis J. Durlofsky · 10 June 2026 · Reservoir Engineering and Simulation Methods

  Data assimilation (DA) in subsurface flow entails calibrating model parameters to match observed data, typically at wells, while preserving geological realism. Latent diffusion models (LDMs) provide efficient mappings from high-dimensional geological model space to a low-dimensional latent variable,…

• EditSSC: Toward Editable Semantic Occupancy Scenes with Unconditional Diffusion Models

  Fatima Balde, Raoul de Charette, Alexandre Boulch · 9 June 2026 · 3D Shape Modeling and Analysis

  3D semantic scene generation is crucial for autonomous driving applications, yet most methods rely on complex 3D-specific architectures such as triplane encoders and adapted diffusion networks, limiting both their simplicity and their editing capabilities. We propose EditSSC, an editing-ready method…

• Less Is More: Training-Free Acceleration Framework of 3D Diffusion Models for Low-Count PET Denoising via Global-Local Trajectory Reduction

  Yuhan Liu, Scott M. Leonard, Marlee Crews, Muhannad Fadhel, Jinkui Hao, Tianqi Chen, Ryan J. Avery, Bo Zhou · 9 June 2026 · Medical Imaging Techniques and Applications

  Accurate quantification and uptake measurement in PET are critical for assessing disease progression and supporting clinical decision-making. While high-count PET provides reliable image quality, the associated radiation dose and prolonged acquisition remain significant clinical concerns, motivating…

• Mitigating Diffusion Model Hallucinations with Dynamic Guidance

  Kostas Triaridis, Alexandros Graikos, Aggelina Chatziagapi, Grigorios G. Chrysos, Dimitris Samaras · 9 June 2026 · Atomic and Subatomic Physics Research

  Hallucinations in diffusion models are samples with structural inconsistencies that can emerge due to the excessive smoothing of the learned score function, which in turn leads to interpolations between modes of the data distribution. Since semantic interpolations are often desirable and contribute …

• Improving Bayesian Optimization via Training-Aware Conditional Diffusion Models

  Yilin Zheng, Haowei Wang, Szu Hui Ng, Enlu Zhou · 9 June 2026 · Gaussian Processes and Bayesian Inference

  Bayesian optimization (BO) is a widely used approach for black-box optimization that uses a Gaussian process (GP) as a surrogate and guides sequential evaluations via an acquisition function, with the ultimate goal of locating the global optimum $\mathbf{x}^{\star}$. To align with this goal, informa…

• Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles

  Xiao Li, Yixuan Jia, Zekai Zhang, Xiang Li, Lianghe Shi, Jinxin Zhou, Zhihui Zhu, Liyue Shen, Qing Qu · 9 June 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion models have demonstrated remarkable generative capabilities and have also emerged as powerful self-supervised representation learners, yet the connection between these two abilities remains less explored. Drawing inspiration from self-supervised learning (SSL), we introduce a framework for…

• IDEQ -- Improving Diffusion Models for the Traveling Salesman Problem (TSP) by Leveraging the Structure of the Solution Space

  Mickael Basson, Philippe Preux · 9 June 2026 · Innovation Policy and R&D

  We investigate diffusion models to solve the Traveling Salesman Problem. Building on the recent DIFUSCO and T2TCO approaches, we propose IDEQ. IDEQ improves the quality of the solutions by leveraging the constrained structure of the state space of the TSP. Another key component of IDEQ consists in r…

• Reconstructing Synthetic SDO/AIA 193 A EUV Images from He I 10830 A Observations with Diffusion Model Translator

  Marco Marena, Qin Li, Haimin Wang, Haodi Jiang, Prajwal Shah, Bo Shen · 9 June 2026 · Solar and Space Plasma Dynamics

  Routine full-disk EUV imaging has been available only since the modern era, such as SOHO and SDO. To extend EUV coronal context into earlier periods, we leverage the multi-decade availability of full-disk \HeI{} observations, whose absorption is modulated by coronal irradiance and magnetic topology …

• Diff-CA: Separating Common and Salient Factors with Diffusion Models

  Michaël Soumm, Alexandre Fournier Montgieux, Yunlong He, Pietro Gori, Alasdair Newson · 5 June 2026 · Generative Adversarial Networks and Image Synthesis

  Contrastive Analysis aims to separate factors that are common between two data distributions from those that are salient to only one of them. Existing contrastive methods are based on generative models (e.g., VAEs or GANs) that often suffer from limited reconstruction and image quality, which hamper…

• FontFusion: Enhancing Generative Text in Diffusion Models with Typographic Conditioning

  Marian Lupascu, Nipun Jindal, Ionut Mironica, Zhaowen Wang · 5 June 2026 · Handwritten Text Recognition Techniques

  Typography generation in diffusion models faces a persistent trade-off: enabling precise font control typically degrades text legibility, while maintaining readability often sacrifices typographic fidelity. We present FontFusion, a plug-and-play conditioning framework for Diffusion Transformer (DiT)…

• ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE

  Mishan Aliev, Eva Neudachina, Ilya Bykov, Aleksandr Oganov, Kirill Struminsky, Aibek Alanov, Denis Rakitin · 5 June 2026 · Generative Adversarial Networks and Image Synthesis

  Modern diffusion models generate high-quality images and videos, but their iterative denoising process makes inference expensive. Feature caching accelerates sampling by reusing or predicting intermediate activations across neighboring denoising steps, exploiting the redundancy of computations along…

• Geometry-Aware Dataset Condensation for Diffusion Model Training

  Xiao Cui, Yulei Qin, Mo Zhu, Wengang Zhou, Hongsheng Li, Houqiang Li · 5 June 2026 · Generative Adversarial Networks and Image Synthesis

  Dataset condensation aims to construct compact datasets from real data via synthesis or selection. However, existing approaches are ill-suited for diffusion model training: synthetic data generation often yields low-fidelity samples unsuitable for authentic modeling, while real subset selection typi…

• Generating Graph-Like Logical Rules for Knowledge Graph Reasoning via Diffusion Models

  Haoxiang Cheng, Yunfei Wang, Chao Chen, Kewei Cheng, Zhipeng Lin, Haoxuan Li, Changjun Fan, Shixuan Liu · 5 June 2026 · Advanced Graph Neural Networks

  Logical rules constitute a cornerstone of knowledge graph (KG) reasoning, valued for their interpretability and ability to model relational patterns. However, existing rule mining methods predominantly focus on simple chain-like rules and therefore neglect the richer relational information encoded i…

• Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit Correction

  Hongkun Dou, Zike Chen, Fengji Li, Hongjue Li, Yue Deng · 5 June 2026 · Diffusion and Search Dynamics

  Controllable generation with discrete diffusion models is often hindered by high computational overhead or the need for retraining. In this paper, we present \underline{\textbf{G}}radient-\underline{\textbf{I}}nformed \underline{\textbf{L}}ogit \underline{\textbf{C}}orrection (\textbf{GILC}), a plug…

• The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show

  Parsa Esmati, Somjit Nath, Katja Hofmann, Derek Nowrouzezahrai, Samira Ebrahimi Kahou, Majid Mirmehdi · 5 June 2026 · Generative Adversarial Networks and Image Synthesis

  Modern video diffusion models generate increasingly realistic and temporally coherent videos, motivating their use as candidate world simulators. Yet it remains unclear whether these models internally encode physical structure, or merely reproduce motion patterns seen during training. We study this …

• The Score Hamiltonian: Mapping Diffusion Models to Adiabatic Transport

  Peter Halmos, Boris Hanin · 5 June 2026 · Quantum many-body systems

  We exhibit an exact correspondence between sampling with score-based diffusion models and adiabatic transport of ground states for a family of Schr\"odinger operators we call Score Hamiltonians, built from the learned score's quantum potential. We obtain novel density reconstruction bounds and princ…

• Efficient and Training-Free Single-Image Diffusion Models

  Haojun Qiu, Kiriakos N. Kutulakos, David B. Lindell · 4 June 2026 · Generative Adversarial Networks and Image Synthesis

  We consider the problem of generating images whose internal structure -- defined by the distribution of patches across multiple scales -- matches that of a single reference image. Recent approaches address this problem by training a diffusion model on a single image. But even in this setting, traini…

• Video-Mirai: Autoregressive Video Diffusion Models Need Foresight

  Yonghao Yu, Lang Huang, Runyi Li, Zerun Wang, Toshihiko Yamasaki · 3 June 2026 · Generative Adversarial Networks and Image Synthesis

  Causal video generators must predict from the past, but they need not learn only from it. In streaming autoregressive video diffusion, each emitted segment becomes a commitment that future segments must preserve. Standard training, however, only asks each causal state to explain the present. This cr…

• A Quantitative Approximation Framework for Flow Distillation in Diffusion Models

  Weiguo Gao, Ming Li, Lei Shi, Hanfei Zhou · 3 June 2026 · Model Reduction and Neural Networks

  We develop a quantitative approximation framework for diffusion distillation, viewing few-step sampling as error propagation under compositions of learned flow maps. Focusing on trajectory distillation for the probability-flow ODE, we show that local approximation errors can be strongly amplified in…

• Bayesian Tensor Decomposition with Diffusion Model Prior

  Zerui Tao, Qibin Zhao · 3 June 2026 · Tensor decomposition and applications

  Low-rank tensor decomposition (TD) is usually effective on clean, fully observed data, but it often degrades under severe missingness or noise. Low-rankness is itself a useful but limited structural prior, and additional handcrafted priors (e.g., sparsity or smoothness) still fall short of capturing…

• Wavelet Fourier Diffuser: Frequency-Aware Diffusion Model for Reinforcement Learning

  Yifu Luo, Yongzhe Chang, Xueqian Wang · 3 June 2026 · Reinforcement Learning in Robotics

  Diffusion probability models have shown significant promise in offline reinforcement learning by directly modeling trajectory sequences. However, existing approaches primarily focus on time-domain features while overlooking frequency-domain features, leading to frequency shift and degraded performan…

• Conditional Latent Diffusion Model with Fourier-based Motion Modelling for Virtual Population Synthesis

  Shaokun Lan, Haoran Dou, Jinghan Huang, Arezoo Zakeri, Fengming Lin, Zherui Zhou, Jinming Duan, Alejandro F. Frangi · 3 June 2026 · Generative Adversarial Networks and Image Synthesis

  In-silico trials of medical devices require the generation of virtual populations of anatomies. In cardiovascular applications, virtual anatomy is typically represented as a 3D+t mesh sampled from a generative model. However, most existing mesh generators focus on static anatomy, while sequence mode…

• AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking

  Jungkyu Kim, Taeyoung Park, Kibok Lee · 3 June 2026 · Generative Adversarial Networks and Image Synthesis

  Score-based diffusion models have emerged as prominent deep generative models; however, their application to tabular data remains challenging because their backbones assume fully specified inputs, whereas real-world tabular data often contain missing values. We propose AugMask, a plug-and-play train…

• Are we really tilting? The mechanics of reward guidance in flow and diffusion models

  Sanjit Dandapanthula, Nicholas M. Boffi · 3 June 2026 · Generative Adversarial Networks and Image Synthesis

  Reward guidance algorithms steer a learned generative process toward the reward-tilted measure at inference time. While empirically powerful, these methods are prone to reward hacking: the guided model over-optimizes the reward at the cost of fidelity to the learned distribution. Prior work has attr…

• Training-free image inversion for one-step diffusion models

  Tao Wu, Senmao Li, Yaxing Wang, Shiqi Yang, Kai Wang, Joost van de Weijer · 2 June 2026 · Generative Adversarial Networks and Image Synthesis

  In this work, we introduce a novel training-free inversion (TFinv) framework for one-step diffusion models,addressing key challenges in real image inversion and editing. We first identify two critical factors hamperingreal-image inversion and editing: (1) Initial Latent Editability, which is related…