Search: diffusion models

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

• FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models

  Abtin Mahyar, Masoumeh Shafieinejad, Yuhan Liu, Xi He · 13 May 2026 · Privacy-Preserving Technologies in Data

  Diffusion models are the leading approach for tabular data synthesis and are increasingly used to share sensitive records. Whether they actually protect privacy has become a pressing question. Membership inference attacks are the standard tool for this purpose, yet existing attacks assume a single-t…

• Efficient Adjoint Matching for Fine-tuning Diffusion Models

  Jeongwoo Shin, Dongsoo Shin, Joonseok Lee, Jaewoong Choi, Jaemoo Choi · 13 May 2026 · Generative Adversarial Networks and Image Synthesis

  Reward fine-tuning has become a common approach for aligning pretrained diffusion and flow models with human preferences in text-to-image generation. Among reward-gradient-based methods, Adjoint Matching (AM) provides a principled formulation by casting reward fine-tuning as a stochastic optimal con…

• Couple to Control: Joint Initial Noise Design in Diffusion Models

  Jing Jia, Liyue Shen, Guanyang Wang · 13 May 2026 · Computer Graphics and Visualization Techniques

  Diffusion models typically generate image batches from independent Gaussian initial noises. We argue that this independence assumption is only one choice within a broader class of valid joint noise designs. Instead, one can specify a coupling of the initial noises: each noise remains marginally stan…

• A PDE Perspective on Generative Diffusion Models

  Kang Liu, Enrique Zuazua · 13 May 2026 · Model Reduction and Neural Networks

  Score-based diffusion models have emerged as a powerful class of generative methods, achieving state-of-the-art performance across diverse domains. Despite their empirical success, the mathematical foundations of those models remain only partially understood, particularly regarding the stability and…

• A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse

  Moongyu Jeon, Sangwoo Shin, BumJun Kim, Kyelim Lee, Albert No · 13 May 2026 · Domain Adaptation and Few-Shot Learning

  Autoregressive language models (ARMs) suffer from the reversal curse: after learning ''$A$ is $B$,'' they often fail on the reverse query ''$B$ is $A$.'' Masked diffusion language models (MDMs) exhibit this failure in a much weaker form, but the underlying reason has remained unclear. A common expla…

• Is Monotonic Sampling Necessary in Diffusion Models?

  Muhammad Haris Khan · 13 May 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion models generate samples by iteratively denoising a Gaussian prior, traversing a sequence of noise levels that, in every published sampler, decreases monotonically. Six years of intensive work has refined nearly every aspect of this recipe, including the corruption operator, the training ob…

• Product-of-Gaussian-Mixture Diffusion Models for Joint Nonlinear MRI Reconstruction

  Laurenz Nagler, Martin Zach, Thomas Pock · 12 May 2026 · Advanced Neuroimaging Techniques and Applications

  Recently, diffusion models have attracted considerable attention for magnetic resonance image reconstruction due to their high sample quality. However, most existing methods rely on large networks with opaque time-conditioning mechanisms, and require offline coil sensitivity estimation. This results…

• Filtering Memorization from Parameter-Space in Diffusion Models

  Yu Zhe, Yang Jiayan, Wei Junhao, Yu-Lin Tsai, Wang Chen · 12 May 2026 · Generative Adversarial Networks and Image Synthesis

  Low-Rank Adaptation (LoRA) has become a widely used mechanism for customizing diffusion models, enabling users to inject new visual concepts or styles through lightweight parameter updates. However, LoRAs can memorize training images, causing generated outputs to reproduce copyrighted or sensitive c…

• Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models

  Yicheng Ji, Zhizhou Zhong, Jun Zhang, Qin Yang, XiTai Jin, Ying Qin, Wenhan Luo, Shuiyang Mao, Wei Liu, Huan Li · 12 May 2026 · Image and Video Quality Assessment

  Autoregressive (AR) video diffusion models adopt a streaming generation framework, enabling long-horizon video generation with real-time responsiveness, as exemplified by the Self Forcing training paradigm. However, existing AR video diffusion models still suffer from significant attention complexit…

• PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models

  Yongsen Cheng, Kai Liu, Kaiwen Tao, Junxian Li, Zhixin Wang, Zhikai Chen, Renjing Pei, Yulun Zhang · 12 May 2026 · Advanced Neural Network Applications

  Large-scale visual generative models have achieved remarkable performance. However, their high computational and memory costs make deployment challenging in resource-constrained scenarios, such as interactive applications and personal single-GPU usage. Post-training quantization (PTQ) offers a pract…

• TARO: Temporal Adversarial Rectification Optimization Using Diffusion Models as Purifiers

  Daniel Wesego, Pedram Rooshenas · 12 May 2026 · Adversarial Robustness in Machine Learning

  Adversarial purification with diffusion models seeks to project adversarial examples back toward the data manifold, but balancing semantic preservation and robustness against adaptive attacks remains challenging. Recent work shows that standard diffusion purification can fail under adaptive evaluati…

• Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study

  Yuhan Wang, Zihan Li, Han Liu, Simon Arberet, Martin Kraus, Yuyin Zhou, Florin-Cristian Ghesu, Dorin Comaniciu, Ali Kamen, Riqiang Gao · 12 May 2026 · Advanced Radiotherapy Techniques

  Voxel-wise dose prediction is a critical yet challenging task in practical radiotherapy (RT) planning, as bespoke models trained from scratch often struggle to generalize across diverse clinical settings. Meanwhile, generative models trained on billion-scale datasets from vision domains have achieve…

• AtteConDA: Attention-Based Conflict Suppression in Multi-Condition Diffusion Models and Synthetic Data Augmentation

  Shogo Noguchi · 12 May 2026 · Advanced Neural Network Applications

  Recent conditional image generation methods can improve controllability by generating images that are faithful to conditions such as sketches, human poses, segmentation maps, and depth. By applying these techniques to image augmentation while preserving annotations, generated images can be used as a…

• NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training

  Fang Wu, Haokai Zhao, Da Xing, Hanqun Cao, Tinson Xu, Yanchao Li, Xiangru Tang, Zehong Wang, Aaron Tu, Kuan Pang, Hanchen Wang, Hongbin Lin, Zeqi Zhou, Yinxi Li, Peng Xia, Li Erran Li, Molei Tao, Jure Leskovec, Aditya Joshi, Yejin Choi · 12 May 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion models have achieved remarkable success across a wide range of generative tasks, yet their training paradigm largely treats injected noise as uniformly informative. In this work, we challenge this assumption and introduce NoiseRater, a meta-learning framework for instance-level noise valua…

• The Safety-Aware Denoiser for Text Diffusion Models

  Amman Yusuf, Zhejun Jiang, Mijung Park · 12 May 2026 · Generative Adversarial Networks and Image Synthesis

  Recent work on text diffusion models offers a promising alternative to autoregressive generation, but controlling their safety remains underexplored. Existing safety approaches are geared toward autoregressive models and typically rely on post-hoc filtering or inference-time interventions. These are…

• SynerDiff: Synergetic Continuous Batching for Fast and Parallel Diffusion Model Inference

  Ziqi Zhou, Peng Yang, Yuxin Liang, Mingliu Liu, Jia Lu · 12 May 2026 · Image and Video Quality Assessment

  The expansion of Artificial Intelligence-generated content service requires diffusion model serving to simultaneously achieve high throughput and low task end-to-end (E2E) latency. However, existing continuous batching methods suffer from severe resource contention during UNet-VAE concurrency, leadi…

• HEART: Hyperspherical Embedding Alignment via Kent-Representation Traversal in Diffusion Models

  Arani Roy, Shristi Das Biswas, Kaushik Roy · 11 May 2026 · Generative Adversarial Networks and Image Synthesis

  Text-to-image diffusion models can generate visually stunning images, yet, controlling what appears and how it appears, remains surprisingly difficult, especially when operating solely within the constraints of the text-conditioning space. For example, changing a subject or adjusting an attribute of…

• SARA: Semantically Adaptive Relational Alignment for Video Diffusion Models

  Jiesong Lian, Zixiang Zhou, Ruizhe Zhong, Yuan Zhou, Qinglin Lu, Rui Wang, Long Hu, Yixue Hao, Baoru Huang · 11 May 2026 · Generative Adversarial Networks and Image Synthesis

  Recent video diffusion models (VDMs) synthesize visually convincing clips, yet still drop entities, mis-bind attributes, and weaken the interactions specified in the prompt. Representation-alignment objectives such as VideoREPA and MoAlign improve fine-grained text following by distilling spatio-tem…

• When Diffusion Model Can Ignore Dimension: An Entropy-Based Theory

  Ahmad Aghapour, Erhan Bayraktar · 11 May 2026 · Advanced Neuroimaging Techniques and Applications

  Diffusion models perform remarkably well on high-dimensional data such as images, often using only a modest number of reverse-time steps. Despite this practical success, existing convergence theory does not fully explain why such samplers remain efficient in high dimensions. Many prior KL guarantees…

• Test-Time Compositional Generalization in Diffusion Models via Concept Discovery

  Zekun Wang, Anant Gupta, Tianyi Zhu, Christopher J. MacLellan · 11 May 2026 · Bayesian Methods and Mixture Models

  Compositional generalization requires models to produce novel configurations from familiar parts. In diffusion models, prior compositional generation methods typically assume that the relevant concepts or conditioning signals are already available. We instead ask whether a pretrained diffusion model…

• On Privacy Leakage in Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics

  Masoumeh Shafieinejad, D. B. Emerson, Behnoosh Zamanlooy, Elaheh Bassak, Fatemeh Tavakoli, Sara Kodeiri, Marcelo Lotif, Xi He · 11 May 2026 · Privacy-Preserving Technologies in Data

  Tabular data plays an important role in many fields and industries, including those with elevated privacy considerations and risks. As such, there is a rising interest in generating high-quality synthetic proxies for real tabular data as a means of reducing privacy risk and proprietary data exposure…

• Secure Seed-Based Multi-bit Watermarking for Diffusion Models from First Principles

  Enoal Gesny, Eva Giboulot · 8 May 2026 · Advanced Steganography and Watermarking Techniques

  The rapid emergence of generative image models has led to the development of specialized watermarking techniques, particularly in-generation methods such as seed-based embedding. However, current evaluations in this area remain largely empirical, making them heavily reliant on the specific model arc…

• Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models

  Zhikai Li, Yue Zhao, Edward Zhongwei Zhang, Xuewen Liu, Jing Zhang, Qingyi Gu, Zhen Dong · 8 May 2026 · Generative Adversarial Networks and Image Synthesis

  Reinforcement learning from human feedback (RLHF) effectively promotes preference alignment of text-to-image (T2I) diffusion models. To improve computational efficiency, direct preference optimization (DPO), which avoids explicit reward modeling, has been widely studied. However, its reliance on bin…

• Adding Thermal Awareness to Visual Systems in Real-Time via Distilled Diffusion Models

  Yuchen Guo, Junli Gong, Wenjun Dong, Yiuming Cheung, Weifeng Su · 8 May 2026 · Advanced Neural Network Applications

  Purely RGB-based vision models often fail to provide reliable cues in challenging scenarios such as nighttime and fog, leading to degraded performance and safety risks. Infrared imaging captures heat-emitting sources and provides critical complementary information, but existing high-fidelity fusion …

• R2H-Diff: Guided Spectral Diffusion Model for RGB-to-Hyperspectral Reconstruction

  Songyu Ding, Ronggiang Zhao, Mingchun Sun, Jie Liu · 8 May 2026 · Sparse and Compressive Sensing Techniques

  RGB-to-hyperspectral image reconstruction is a highly ill-posed inverse problem, since multiple plausible spectral distributions may correspond to the same RGB observation. Existing regression-based methods usually learn a deterministic mapping, which limits their ability to model reconstruction unc…