Search: diffusion models

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

• SteeringDiffusion: A Bottlenecked Activation Control Interface for Diffusion Models

  Fangzheng Wu, Brian Summa · 5 May 2026 · Model Reduction and Neural Networks

  We introduce SteeringDiffusion, a bottlenecked activation-level control interface for diffusion models that exposes a smooth, monotonic, and runtime-adjustable control surface over the content--style trade-off. Our method keeps the U-Net backbone frozen and learns a small, prompt-conditioned latent …

• CSGuard: Toward Forgery-Resistant Watermarking in Diffusion Models via Compressed Sensing Constraint

  Jiewei Lai, Lan Zhang, Chen Tang, Pengcheng Sun, Zhaopeng Zhang, Yunhao Wang, Hui Jin · 5 May 2026 · Advanced Steganography and Watermarking Techniques

  Latent-based diffusion model watermarking embeds watermarks into generated images' latent space to enable content attribution, offering a training-free solution for intellectual property protection and digital forensics. However, these methods exhibit a critical vulnerability to the forgery attack, …

• Phase-map synthesis from magnitude-only MR images using conditional score-based diffusion models with application in training of accelerated MRI reconstruction models

  M. Berk Sahin, Dilek Yalcinkaya, Abolfazl Hashemi, Behzad Sharif · 5 May 2026 · Advanced Neuroimaging Techniques and Applications

  Accelerated magnetic resonance imaging (MRI) enabled by the training of deep learning (DL)-based image recon. models requires large and diverse raw k-space datasets. In most clinical MRI applications, due to storage and patient privacy concerns, raw k-space data is discarded and magnitude-only image…

• Disciplined Diffusion: Text-to-Image Diffusion Model against NSFW Generation

  Chi Zhang, Changjia Zhu, Xiaowen Li, Yao Liu, Zhuo Lu · 5 May 2026 · Adversarial Robustness in Machine Learning

  Text-to-image (T2I) diffusion models have the ability to build high-quality pictures from text prompts, but they pose safety concerns because they can generate offensive or disturbing imagery when provided with harmful inputs. Existing safety filters typically rely on text-based classifiers or image…

• Skipping the Zeros in Diffusion Models for Sparse Data Generation

  Phil Sidney Ostheimer, Mayank Nagda, Andriy Balinskyy, Gabriel Vicente Rodrigues, Jean Radig, Carl Herrmann, Stephan Mandt, Marius Kloft, Sophie Fellenz · 5 May 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion models (DMs) excel on dense continuous data, but are not designed for sparse continuous data. They do not model exact zeros that represent the deliberate absence of a signal. As a result, they erase sparsity patterns and perform unnecessary computation on mostly zero entries. With Sparsity…

• Fusing Urban Structure and Semantics: A Conditional Diffusion Model for Cross-City OD Matrix Generation

  Bin Chen, Zhuoya Meng, Fang Yang, Runkang Guo, Jingtao Ding, Yin Zhang, Chuan Ai, Zhengqiu Zhu · 5 May 2026 · Human Mobility and Location-Based Analysis

  Accurate modeling of commuting flows is important for urban governance, traffic planning, and resource allocation. However, the combined influence of individual intentions, geographic constraints, and social dynamics leads to considerable heterogeneity in commuting patterns, making it difficult to d…

• Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding

  An Huang, Junggab Son, Zuobin Xiong · 5 May 2026 · Security and Verification in Computing

  Diffusion models have become the foundation of modern generative systems, with most research focusing primarily on improving generation efficiency and output quality. The timestep embedding component is a crucial part of the diffusion pipeline, which provides a temporal conditioning signal to the de…

• It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models

  Anne Harrington, A. Sophia Koepke, Shyamgopal Karthik, Trevor Darrell, Alexei A. Efros · 4 May 2026 · Generative Adversarial Networks and Image Synthesis

  Contemporary text-to-image models exhibit a surprising degree of mode collapse, as can be seen when sampling several images given the same text prompt. Previous work has attempted to address this issue by steering the model using guidance mechanisms, or by generating a large pool of candidates and r…

• Diffusion Models for Solving Inverse Problems via Posterior Sampling with Piecewise Guidance

  Saeed Mohseni-Sehdeh, Walid Saad, Kei Sakaguchi, Tao Yu · 4 May 2026 · Advanced Image Processing Techniques

  Diffusion models are powerful tools for sampling from high-dimensional distributions by progressively transforming pure noise into structured data through a denoising process. When equipped with a guidance mechanism, these models can also generate samples from conditional distributions. In this pape…

• CollaFuse: Collaborative Diffusion Models

  Simeon Allmendinger, Domenique Zipperling, Lukas Struppek, Niklas K\"uhl · 4 May 2026 · Generative Adversarial Networks and Image Synthesis

  In the landscape of generative artificial intelligence, diffusion-based models have emerged as a promising method for generating synthetic images. However, the application of diffusion models poses numerous challenges, particularly concerning data availability, computational requirements, and privac…

• Trees to Flows and Back: Unifying Decision Trees and Diffusion Models

  Sai Niranjan Ramachandran, Suvrit Sra · 4 May 2026 · Advanced Graph Neural Networks

  Decision trees and diffusion models are ostensibly disparate model classes, one discrete and hierarchical, the other continuous and dynamic. This work unifies the two by establishing a crisp mathematical correspondence between hierarchical decision trees and diffusion processes in appropriate limiti…

• When Do Diffusion Models learn to Generate Multiple Objects?

  Yujin Jeong, Arnas Uselis, Iro Laina, Seong Joon Oh, Anna Rohrbach · 4 May 2026 · Generative Adversarial Networks and Image Synthesis

  Text-to-image diffusion models achieve impressive visual fidelity, yet they remain unreliable in multi-object generation. Despite extensive empirical evidence of these failures, the underlying causes remain unclear. We begin by asking how much of this limitation arises from the data itself. To disen…

• Noise2Map: End-to-End Diffusion Model for Semantic Segmentation and Change Detection

  Ali Shibli, Andrea Nascetti, Yifang Ban · 1 May 2026 · Remote-Sensing Image Classification

  Semantic segmentation and change detection are two fundamental challenges in remote sensing, requiring models to capture either spatial semantics or temporal differences from satellite imagery. Existing deep learning models often struggle with temporal inconsistencies or in capturing fine-grained sp…

• VIPaint: Image Inpainting with Pre-Trained Diffusion Models via Variational Inference

  Sakshi Agarwal, Gabriel Hope, Jimin Heo, Erik B. Sudderth · 1 May 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion probabilistic models learn to remove noise added during training, generating novel data (e.g., images) from Gaussian noise through sequential denoising. However, conditioning the generative process on corrupted or masked images is challenging. While various methods have been proposed for i…

• Simple Self-Conditioning Adaptation for Masked Diffusion Models

  Michael Cardei, Huu Binh Ta, Ferdinando Fioretto · 1 May 2026 · Generative Adversarial Networks and Image Synthesis

  Masked diffusion models (MDMs) generate discrete sequences by iterative denoising under an absorbing masking process. In standard masked diffusion, if a token remains masked after a reverse update, the model discards its clean-state prediction for that position. Thus, still-masked positions must be …

• Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models

  Haosen Li, Wenshuo Chen, Lei Wang, Shaofeng Liang, Bowen Tian, Soning Lai, Yutao Yue · 30 April 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion models have achieved remarkable success in synthesizing complex static and temporal visuals, a breakthrough largely driven by Classifier-Free Guidance (CFG). However, despite its pivotal role in aligning generated content with textual prompts, standard CFG relies on a globally uniform scal…

• Probabilistic data quality assessment for structural monitoring data via outlier-resistant conditional diffusion model

  Qi Li (Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology, School of Civil Engineering, Harbin Institute of Technology, Harbin, 150090, China, Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education, Harbin Institute of Technology, Harbin, 150090, China), Yong Huang (Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology, School of Civil Engineering, Harbin Institute of Technology, Harbin, 150090, China, Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education, Harbin Institute of Technology, Harbin, 150090, China), Hui Li (Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology, School of Civil Engineering, Harbin Institute of Technology, Harbin, 150090, China, Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education, Harbin Institute of Technology, Harbin, 150090, China) · 30 April 2026 · Structural Health Monitoring Techniques

  Data quality assessment is an essential step that ensures the reliability of the subsequent structural health monitoring (SHM) tasks. This study proposes a prediction deviation-based SHM data quality assessment method using a univariate implicit auto-regressive model, enabling outlier diagnosis and …

• Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models

  Zhirong Shen, Rui Huang, Jiacheng Liu, Chang Zou, Peiliang Cai, Shikang Zheng, Zhengyi Shi, Liang Feng, Linfeng Zhang · 30 April 2026 · Generative Adversarial Networks and Image Synthesis

  To address the high sampling cost of Diffusion Transformers (DiTs), feature caching offers a training-free acceleration method. However, existing methods rely on hand-crafted forecasting formulas that fail under aggressive skipping. We propose L2P (Learnable Linear Predictor), a simple data-driven c…

• Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data

  Bao Pham, Mohammed J. Zaki, Luca Ambrogioni, Dmitry Krotov, Matteo Negri · 30 April 2026 · Language and cultural evolution

  When do language diffusion models memorize their training data, and how to quantitatively assess their true generative regime? We address these questions by showing that Uniform-based Discrete Diffusion Models (UDDMs) fundamentally behave as Associative Memories (AMs) $\textit{with emergent creative…

• ACPO: Anchor-Constrained Perceptual Optimization for Diffusion Models with No-Reference Quality Guidance

  Yang Yang, Feifan Meng, Han Fang, Weiming Zhang · 30 April 2026 · Image and Video Quality Assessment

  Diffusion models have achieved remarkable success in image generation, yet their training is predominantly driven by full-reference objectives that enforce pixel-wise similarity to ground-truth images.Such supervision, while effective for fidelity, may insufficient in terms of subjective visual perc…

• Benchmarking Layout-Guided Diffusion Models through Unified Semantic-Spatial Evaluation in Closed and Open Settings

  Luca Parolari, Nicla Faccioli, Lamberto Ballan · 29 April 2026 · Generative Adversarial Networks and Image Synthesis

  Evaluating layout-guided text-to-image generative models requires assessing both semantic alignment with textual prompts and spatial fidelity to prescribed layouts. Assessing layout alignment requires collecting fine-grained annotations, which is costly and labor-intensive. Consequently, current ben…

• Learning Illumination Control in Diffusion Models

  Nishit Anand, Manan Suri, Christopher Metzler, Dinesh Manocha, Ramani Duraiswami · 29 April 2026 · Generative Adversarial Networks and Image Synthesis

  Controlling illumination in images is essential for photography and visual content creation. While closed-source models have demonstrated impressive illumination control, open-source alternatives either require heavy control inputs like depth maps or do not release their data and code. We present a …

• Generative diffusion models for spatiotemporal influenza forecasting

  Joseph Lemaitre, Justin Lessler · 29 April 2026 · COVID-19 epidemiological studies

  Forecasting infectious disease incidence can provide important information to guide public health planning, yet is difficult because epidemic dynamics are complex. Current mechanistic and statistical approaches often struggle to capture multimodal uncertainty or emergent trends. Influpaint adapts de…

• Dual-domain Multi-path Self-supervised Diffusion Model for Accelerated MRI Reconstruction

  Yuxuan Zhang, Jinkui Hao, Bo Zhou · 29 April 2026 · Advanced Neuroimaging Techniques and Applications

  Magnetic resonance imaging (MRI) is a vital diagnostic tool, but its inherently long acquisition times reduce clinical efficiency and patient comfort. Recent advancements in deep learning, particularly diffusion models, have improved accelerated MRI reconstruction. However, existing diffusion models…

• Diffusion Model as a Generalist Segmentation Learner

  Haoxiao Wang, Antao Xiang, Haiyang Sun, Peilin Sun, Changhao Pan, Yifu Chen, Minjie Hong, Weijie Wang, Shuang Chen, Yue Chen, Zhou Zhao · 28 April 2026 · Multimodal Machine Learning Applications

  Diffusion models are primarily trained for image synthesis, yet their denoising trajectories encode rich, spatially aligned visual priors. In this paper, we demonstrate that these priors can be utilized for text-conditioned semantic and open-vocabulary segmentation, and this approach can be generali…