Search: diffusion models

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

• Finding DoRI: Discovery of Retained Images in Diffusion Models

  Antoni Kowalczuk, Dominik Hintersdorf, Lukas Struppek, Kristian Kersting, Adam Dziedzic, Franziska Boenisch · 29 May 2026 · Digital Humanities and Scholarship

  Text-to-image diffusion models (DMs) have achieved remarkable success in image generation. However, concerns about data privacy and intellectual property remain due to their potential to inadvertently memorize and replicate training data. Recent mitigation efforts have focused on identifying and pru…

• Masked Diffusion Modeling for Anomaly Detection

  Lixing Zhang, Yuchen Liang, Liyan Xie · 29 May 2026 · Anomaly Detection Techniques and Applications

  Anomaly detection aims to identify samples that deviate from the nominal data distribution and is central to many safety-critical applications. However, developing effective anomaly detection methods for categorical, mixed-type, and discrete sequence data remains challenging and relatively underexpl…

• Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models

  Jaa-Yeon Lee, Yeobin Hong, Taesung Kwon, Jong Chul Ye · 29 May 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion models generate highly realistic images but often struggle with precise text-image alignment. While recent post-training methods improve alignment using external rewards or human preference signals, their performance heavily depends on reward quality and does not directly address alignment…

• The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models

  Dueun Kim, Albert No · 29 May 2026 · Language and cultural evolution

  Masked diffusion language models (MDMs) uniquely support any-order generation, with confidence-based decoding currently serving as the de facto standard inference policy. To optimize for this, recent training schemes attempt to align training mask patterns directly with those observed during generat…

• Orthogonal Concept Erasure for Diffusion Models

  Yuhao Sun, Lingyun Yu, Haoxiang Xu, Fengyuan Miao, Zhuoer Xu, Hongtao Xie · 29 May 2026 · Domain Adaptation and Few-Shot Learning

  Concept erasure has emerged as a promising approach to mitigate undesired or unsafe content in diffusion models, yet existing methods still face significant limitations. While training-based methods are effective, their high computational cost limits scalability. Editing-based methods are more effic…

• Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales

  Myeongsoo Kim, Eunji Kim, Minwoo Chae, Sangwoo Mo · 28 May 2026 · Ethics and Social Impacts of AI

  Diffusion models steer conditional generation with a tunable guidance scale to trade off prompt alignment and diversity. However, existing debiasing techniques are optimized for a single scale, degrading fairness when users adjust this parameter. We trace this behavior to a previously overlooked sou…

• Representation-Conditioned Diffusion Models for Guided Training Data Generation

  Nithesh Chandher Karthikeyan, Jonas Unger, Gabriel Eilertsen · 28 May 2026 · Generative Adversarial Networks and Image Synthesis

  Data availability remains a critical bottleneck in many deep learning applications. Large-scale datasets are often expensive to collect, curate and annotate, which can limit the scalability and applicability of supervised learning methods. In this work, we evaluate the classification performance of …

• Stage-wise Distortion-Perception Traversal in Zero-shot Inverse Problems with Diffusion Models

  Jiawei Zhang, Ziyuan Liu, Leon Yan, Zhenyu Xiao, Yuantao Gu · 28 May 2026 · Generative Adversarial Networks and Image Synthesis

  The distortion-perception (D-P) tradeoff is a fundamental phenomenon of Bayesian inverse problems, which characterizes the inherent tension between distortion performance and perceptual quality. Enabling flexible traversal of the D-P tradeoff at inference time is crucial for practical applications. …

• Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models

  Ken Takeda, Masafumi Oizumi, Ryo Karakida · 28 May 2026 · Domain Adaptation and Few-Shot Learning

  Generative models, including diffusion models, are increasingly used as foundation models and adapted through sequential fine-tuning, making continual learning an essential problem setting. However, continual learning in such generative models remains poorly understood: after a task change, what asp…

• Explicit Critic Guidance for Aligning Diffusion Models

  Zhengyang Liang, Qihang Zhang, Ceyuan Yang · 28 May 2026 · Reinforcement Learning in Robotics

  Online reinforcement learning is becoming increasingly important for aligning diffusion models with non-differentiable objectives. However, existing methods still face limitations in assigning fine-grained credit along denoising trajectories and in realizing stable value-based optimization. We propo…

• Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models

  Calvin Yeung, Prathyush Poduval, Ali Zakeri, Zhuowen Zou, Mohsen Imani · 28 May 2026 · Advanced Neuroimaging Techniques and Applications

  Text-to-image diffusion models generate images through an iterative denoising process, so internal neural layers produce trajectories of activations rather than single static representations. Sparse autoencoders (SAEs) have recently been used to decompose diffusion activations into interpretable fea…

• Balancing Fidelity and Diversity in Diffusion Models via Symmetric Attention Decomposition: Hopfield Perspective

  Hyunmin Cho, Woo Kyoung Han, Kyong Hwan Jin · 28 May 2026 · Ferroelectric and Negative Capacitance Devices

  We characterize the pre-softmax attention matrix $\mathbf{QK^\top}$ in transformers as an associative memory matrix encoding pairwise associations between input features. By decomposing this matrix into its symmetric and skew-symmetric parts, we interpret the symmetric component as governing the str…

• BlazeEdit: Generalist Image Editing on Mobile Devices with Image-to-Image Diffusion Models

  Fei Deng, Yanwu Xu, Zhipeng Bao, Zhixing Zhang, Haolin Jia, Karthik Raveendran, Jianing Wei · 28 May 2026 · Generative Adversarial Networks and Image Synthesis

  The remarkable generation quality of modern diffusion models often comes at the cost of massive parameter counts, which necessitate server-side inference with significant computational costs and potential privacy risks. Consequently, there is growing momentum toward developing efficient on-device al…

• Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking

  Zhengbo Zhang, Zhigang Tu, Junsong Yuan, De Wen Soh, Bo Du · 27 May 2026 · Video Surveillance and Tracking Methods

  Unsupervised visual object tracking is a challenging task that requires following arbitrary targets in videos without training on ground-truth annotations. Despite considerable progress, existing state-of-the-art unsupervised trackers often struggle in scenarios that demand fine-grained understandin…

• A Unified Framework for Diffusion Model Unlearning with f-Divergence

  Nicola Novello, Federico Fontana, Luigi Cinque, Deniz Gunduz, Andrea M. Tonello · 27 May 2026 · Matrix Theory and Algorithms

  Most existing methods for concept unlearning in text-to-image diffusion models minimize a mean squared error (MSE) loss between the denoiser outputs conditioned on a target and an anchor concept, which is implicitly the KL divergence between two Gaussians. We generalize this objective to any $f$-div…

• Towards Controllable Image Generation through Representation-Conditioned Diffusion Models

  Nithesh Chandher Karthikeyan, Jonas Unger, Gabriel Eilertsen · 27 May 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion models have emerged as powerful tools for high-quality image generation and editing, but guiding these models to produce specific outputs remains a challenge. Conventional approaches rely on conditioning mechanisms, such as text prompts or semantic maps, which require extensively annotated…

• From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models

  Yuchen Liang, Ness Shroff, Yingbin Liang · 27 May 2026 · Generative Adversarial Networks and Image Synthesis

  Discrete diffusion models have achieved strong empirical performance in text and other symbolic domains, but, especially for uniform-rate models, they often require many steps to generate a single sample. Existing acceleration methods either rely on training additional quantities or suffer from slow…

• Localizing Memorized Regions in Diffusion Models via Coordinate-Wise Curvature Differences

  Gwangho Kim, Sungyoon Lee · 27 May 2026 · Face recognition and analysis

  Diffusion models can unintentionally memorize training samples, raising concerns about privacy and copyright. While recent methods can detect memorization, they often rely on global or model-specific signals and provide limited insight into where memorization appears within a generated image. We pro…

• RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models

  Xing Cong, Hanlin Tang, Kan Liu, Lan Tao, Lin Qu, Chenhao Xie · 27 May 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs. While prior work has reduced this cost via quantization and distillation, semi-structured sparsity, which can nearly halve FLOPs, remains underexplored. A key reason is that most existi…

• Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models

  Austin Wang, Jiaqi Han, Stefano Ermon, Yisong Yue · 27 May 2026 · Generative Adversarial Networks and Image Synthesis

  Preference optimization has emerged as an efficient alternative to online reinforcement learning from human feedback (RLHF) for aligning text-to-image diffusion models. However, existing methods largely reduce supervision to binary pairwise comparisons. This pairwise reduction is limiting when train…

• Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolution

  Junseo Bang, Joonhee Lee, Kyeonghyun Lee, Haechang Lee, Dong Un Kang, Se Young Chun · 27 May 2026 · Advanced Image Processing Techniques

  Arbitrary-scale image super-resolution aims to upsample images to any desired resolution, offering greater flexibility than traditional fixed-scale super-resolution. Recent approaches based on regression-based or generative models have shown promising results but often suffer from scale inconsistenc…

• Diffuse to Detect: Generative Diffusion Models for Unsupervised IC Anomaly Detection

  Yuxuan Yin, Chen He, Todd Jacobs, Jialei He, Boxun Xu, Robert Jin, Peng Li · 27 May 2026 · Anomaly Detection Techniques and Applications

  Latent defect screening is challenged by extremely low failure rates, high-dimensional test data, and absence of labeled anomalies. We propose the first unsupervised anomaly detection framework incorporating a Diffusion Transformer. Raw test measurements are first compressed by an autoencoder, then …

• Erased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion Models

  Arian Komaei Koma, Seyed Amir Kasaei, AmirMahdi Sadeghzadeh, Mohammad Hossein Rohban · 27 May 2026 · Adversarial Robustness in Machine Learning

  Machine unlearning aims to remove specific concepts from pretrained text-to-image diffusion models, yet several white- and black-box attacks have been introduced to make the model generate such unlearned concepts. These attacks, nevertheless, do not assume a realistic threat model, i.e. they either …

• Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models

  Yiwei Xie, Ping Liu, Zheng Zhang · 26 May 2026 · Generative Adversarial Networks and Image Synthesis

  Text-to-video diffusion transformers encode semantic information unevenly across model depth, which constrains effective concept erasure. We identify a representational bottleneck, termed concept-layer topological alignment, under which target concepts exhibit higher separability at certain represen…

• AI-T2I: Aggregating-and-Isolating Cross-Attention to Diffusion Models for Text-to-Image Synthesis

  Shipeng Cao, Biao Qian, Haipeng Liu, Yang Wang, Meng Wang · 26 May 2026 · Generative Adversarial Networks and Image Synthesis

  Text-to-image synthesis has made significant progress, benefiting from the strong generative capabilities of diffusion models. However, these models struggle to achieve precise text-to-image alignment within cross-attention maps during the denoising process. Existing works primarily focus on inter-s…