Search: diffusion models

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

• Defending Diffusion Models Against Membership Inference Attacks via Higher-Order Langevin Dynamics

  Benjamin Sterling, Yousef El-Laham, M\'onica F. Bugallo · 8 May 2026 · Advanced Mathematical Modeling in Engineering

  Recent advances in generative artificial intelligence applications have raised new data security concerns. This paper focuses on defending diffusion models against membership inference attacks. This type of attack occurs when the attacker can determine if a certain data point was used to train the m…

• The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Models

  Flavio Nicoletti, Chenxiao Ma, Enrico Ventura, Luca Saglietti, Stefano Sarao Mannelli · 8 May 2026 · Generative Adversarial Networks and Image Synthesis

  Real-world datasets are inherently heterogeneous, yet how per-class structural differences and sampling imbalance shape the training dynamics of diffusion models-and potentially exacerbate disparities-remains poorly understood. While models typically transition from an initial phase of generalizatio…

• Diffusion model for SU(N) gauge theories

  Javad Komijani, Marina K. Marinkovic, Lara Turgut · 8 May 2026 · Bayesian Methods and Mixture Models

  Implicit score matching provides a computationally efficient approach for training diffusion models and generating high-quality samples from complex distributions. In this work, we develop a score-matching framework for SU(N) lattice gauge theories, which can be extended to other Lie groups. We appl…

• Diverse Sampling in Diffusion Models with Marginal Preserving Particle Guidance

  Gal Vinograd, Idan Achituve, Ethan Fetaya · 8 May 2026 · Generative Adversarial Networks and Image Synthesis

  We present EDDY (Exact-marginal Diversification via Divergence-free dYnamics), a guidance mechanism for diffusion and flow matching models that promotes diversity among samples generated while maintaining quality. EDDY exploits symmetries of the Fokker-Planck equation, using drift perturbations that…

• Understanding diffusion models requires rethinking (again) generalization

  Pierre Marion, Yu-Han Wu · 8 May 2026 · Neural Networks and Applications

  This position paper argues that understanding generalization in diffusion models requires fundamentally new theoretical frameworks that go beyond both classical statistical learning theory and the benign overfitting paradigm developed for supervised learning. In diffusion models, unlike in supervise…

• Bayesian Rain Field Reconstruction using Commercial Microwave Links and Diffusion Model Priors

  Badr Moufad, Albina Ilina, Hai Victor Habi, Salem Lahlou, Yazid Janati, Hagit Messer, Eric Moulines · 8 May 2026 · Precipitation Measurement and Analysis

  Commercial Microwave Links (CMLs) offer dense spatial coverage for rainfall sensing but produce path-integrated measurements that make accurate ground-level reconstruction challenging. Existing methods typically oversimplify CMLs as point sensors and neglect line integration relating rainfall to sig…

• D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models

  Dengyang Jiang, Xin Jin, Dongyang Liu, Zanyi Wang, Mingzhe Zheng, Ruoyi Du, Xiangpeng Yang, Qilong Wu, Zhen Li, Peng Gao, Harry Yang, Steven Hoi · 7 May 2026 · Generative Adversarial Networks and Image Synthesis

  The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterparts (e.g, Z-Image-Turbo and FLUX.2-klein). However, these models present significant challenges for direct continuous supervised fine-tuning. For ex…

• Computer-Aided Design Generation by Cascaded Discrete Diffusion Model

  Honghu Pan, Xiaoling Luo, Yongyong Chen, Zhenyu He, Pengyang Wang · 7 May 2026 · 3D Shape Modeling and Analysis

  Recent deep learning approaches seek to automate CAD creation by representing a model as a sequence of discrete commands and parameters, and then generating them using autoregressive models or continuous diffusion operating in Euclidean embedding space. However, continuous diffusion perturbs represe…

• Deep Dreams Are Made of This: Visualizing Monosemantic Features in Diffusion Models

  Adam Szokalski, Mateusz Modrzejewski · 7 May 2026 · Generative Adversarial Networks and Image Synthesis

  This paper proposes latent visualization by optimization (LVO), a mechanistic interpretability technique that extends feature visualization by optimization - originally developed for convolutional neural networks - to latent diffusion models. LVO employs sparse autoencoders (SAEs) to disentangle pol…

• DiCLIP: Diffusion Model Enhances CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation

  Zhiwei Yang, Pengfei Song, Yucong Meng, Kexue Fu, Shuo Wang, Zhijian Song · 7 May 2026 · Multimodal Machine Learning Applications

  Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically leverages Class Activation Maps (CAMs) to achieve pixel-level predictions. Recently, Contrastive Language-Image Pre-training (CLIP) has been introduced to generate CAMs in WSSS. However, previous WSSS methods solely ado…

• Concurrence of Symmetry Breaking and Nonlocality Phase Transitions in Diffusion Models

  Yifan F. Zhang, Fangjun Hu, Guangkuo Liu, Mert Okyay, Xun Gao · 7 May 2026 · Theoretical and Computational Physics

  Diffusion models undergo a phase transition in a critical time window during generation dynamics, with two complementary diagnoses of criticality. The symmetry breaking picture views the critical window as when trajectories bifurcate into different semantic minima of the energy landscape, whereas th…

• Towards General Preference Alignment: Diffusion Models at Nash Equilibrium

  Jiaming Hu, Jiamu Bai, Haoyu Wang, Debarghya Mukherjee, Ioannis Ch. Paschalidis · 7 May 2026 · Mobile Crowdsensing and Crowdsourcing

  Reinforcement learning from human feedback (RLHF) has been popular for aligning text-to-image (T2I) diffusion models with human preferences. As a mainstream branch of RLHF, Direct Preference Optimization (DPO) offers a computationally efficient alternative that avoids explicit reward modeling and ha…

• Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models

  Bartlomiej Sobieski, Matthew Tivnan, Dawid P{\l}udowski, Micha{\l} Jan W{\l}odarczyk, Pengfei Jin, Przemyslaw Biecek, Quanzheng Li · 7 May 2026 · Topological and Geometric Data Analysis

  Diffusion models are prone to generating structural hallucinations - samples that match the statistical properties of the training data yet defy underlying structural rules, resulting in anomalies like hands with more than five fingers. Recent research studied this failure mode from several viewpoin…

• Stage-adaptive audio diffusion modeling

  Xuanhao Zhang, Chang Li · 7 May 2026 · Hearing Loss and Rehabilitation

  Recent progress in diffusion-based audio generation and restoration has substantially improved performance across heterogeneous conditioning regimes, including text-conditioned audio generation and audio-conditioned super-resolution. However, training audio diffusion models remains computationally e…

• DMGD: Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Models

  Qichao Wang, Yunhong Lu, Hengyuan Cao, Junyi Zhang, Min Zhang · 6 May 2026 · Generative Adversarial Networks and Image Synthesis

  Dataset distillation enables efficient training by distilling the information of large-scale datasets into significantly smaller synthetic datasets. Diffusion based paradigms have emerged in recent years, offering novel perspectives for dataset distillation. However, they typically necessitate addit…

• Concept-based Visual Counterfactual Explanations with Diffusion Models

  Yassine Oueslati, Daniil Kirilenko, Martin Gjoreski, Marc Langheinrich · 6 May 2026 · Generative Adversarial Networks and Image Synthesis

  Visual counterfactual explanations aim to answer "what minimal change to this image would flip the model's prediction?", and are increasingly important as vision models are deployed in safety-critical domains (e.g., medicine). Existing diffusion-based methods can produce realistic edits, but they re…

• Metadata, Wavelet, and Time Aware Diffusion Models for Satellite Image Super Resolution

  Luigi Sigillo, Renato Giamba, Danilo Comminiello · 6 May 2026 · Advanced Image Processing Techniques

  The acquisition of high-resolution satellite imagery is often constrained by the spatial and temporal limitations of satellite sensors, as well as the high costs associated with frequent observations. These challenges hinder applications such as environmental monitoring, disaster response, and agric…

• Quaternion Wavelet-Conditioned Diffusion Models for Image Super-Resolution

  Luigi Sigillo, Christian Bianchi, Aurelio Uncini, Danilo Comminiello · 6 May 2026 · Image and Signal Denoising Methods

  Image Super-Resolution is a fundamental problem in computer vision with broad applications spacing from medical imaging to satellite analysis. The ability to reconstruct high-resolution images from low-resolution inputs is crucial for enhancing downstream tasks such as object detection and segmentat…

• Joint Relational Database Generation via Graph-Conditional Diffusion Models

  Mohamed Amine Ketata, David L\"udke, Leo Schwinn, Stephan G\"unnemann · 6 May 2026 · Data Quality and Management

  Building generative models for relational databases (RDBs) is important for many applications, such as privacy-preserving data release and augmenting real datasets. However, most prior works either focus on single-table generation or adapt single-table models to the multi-table setting by relying on…

• Towards accurate extreme event likelihoods from diffusion model climate emulators

  Peter Manshausen, Noah Brenowitz, Julius Berner, Karthik Kashinath, Mike Pritchard · 6 May 2026 · Climate variability and models

  ML climate model emulators are useful for scenario planning and adaptation, allowing for cost-efficient experimentation. Recently, the diffusion model Climate in a Bottle (cBottle) has been proposed for generation of atmospheric states compatible with boundary conditions of solar position and sea su…

• Stochastic Schr\"odinger Diffusion Models for Pure-State Ensemble Generation

  Jian Xu, Wei Chen. Chao Li, Jingyuan Zheng, Delu Zeng, John Paisley, Qibin Zhao · 6 May 2026 · Quantum many-body systems

  In quantum machine learning (QML), classical data are often encoded as quantum pure states and processed directly as quantum representations, motivating representation-level generative modeling that samples new quantum states from an underlying pure-state ensemble rather than re-preparing them from …

• GRIFDIR: Graph Resolution-Invariant FEM Diffusion Models in Function Spaces over Irregular Domains

  James Rowbottom, Elizabeth L. Baker, Nick Huang, Ben Adcock, Carola-Bibiane Sch\"onlieb, Alexander Denker · 6 May 2026 · Advanced Graph Neural Networks

  Score-based diffusion models in infinite-dimensional function spaces provide a mathematically principled framework for modelling function-valued data, offering key advantages such as resolution invariance and the ability to handle irregular discretisations. However, practical implementations have st…

• Stylistic Attribute Control in Latent Diffusion Models

  Max Reimann, Benito Buchheim, Jürgen Döllner · 5 May 2026 · Generative Adversarial Networks and Image Synthesis

  Text-to-image diffusion models have revolutionized image synthesis and editing, but precise control over stylistic attributes remains a challenge, often causing unintended content modifications. We propose an approach for fine-grained parametric control of stylistic attributes in latent diffusion mo…

• SlimDiffSR: Toward Lightweight and Efficient Remote Sensing Image Super-Resolution via Diffusion Model Distillation

  Ce Wang, Zhenyu Hu, Wanjie Sun · 5 May 2026 · Advanced Image Processing Techniques

  Diffusion models have recently achieved remarkable performance in image super-resolution (SR), but their high computational cost limits practical deployment in remote sensing applications. To address this issue, we propose SlimDiffSR, a lightweight and efficient diffusion-based framework for real-wo…

• Exploring Data-Free LoRA Transferability for Video Diffusion Models

  Yuchen Wang, Wenliang Zhong, Lichen Bai, Zikai Zhou, Shitong Shao, Bojun Cheng, Shuo Chen, Shuo Yang, Zeke Xie · 5 May 2026 · Generative Adversarial Networks and Image Synthesis

  Video diffusion models leveraging step distillation or causal distillation have achieved remarkable performance. However, adapting existing LoRAs to these variants remains a critical challenge due to weight space mismatches. We observe that direct application leads to style degradation and structura…