Búsqueda: diffusion models

Más de 1000 artículos coinciden: estos son los 1000 más recientes, ordenados por relevancia.

• Sobolev Regularized Score Difference Estimation in Diffusion Models

  Chenghan Xie, Jose Blanchet, Renyuan Xu · 20 de agosto de 2026 · Advanced Mathematical Modeling in Engineering

  Estimating the difference of two Stein's score functions is a fundamental problem in generative modeling. In particular, score differences arise naturally in transfer learning, where the score difference provides the mechanism for adapting a pre-trained model to a new target distribution, and in dif…

• Diff-DDoS: Realistic Cyber-Physical Attack Synthesis and Robust Detection for 5G-Enabled CPS Using Tabular Diffusion Models

  Bilal Hussain, Xiao Tang, Qinghe Du, Tan Li, Muhammad Azhar, Danista Khan · 19 de agosto de 2026 · Smart Grid Security and Resilience

  Deep learning-based DDoS detectors for 5G-enabled cyber-physical systems face scarce labeled attack data and unrealistic synthetic substitutes, which limit robustness against adaptive adversaries. Detectors trained on hand-crafted attacks with fixed scaling multipliers degrade catastrophically (F1-s…

• LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching

  Jinshan Liu, Haoran Qin, Xiaobing Tu, Jiacheng Liu, Jiahui Hu, Zhengan Yan, Yukun Xie, Kerui Shen, Jinkui Ren, Yuqi Lin, Xiantao Zhang, Linfeng Zhang · 19 de agosto de 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion models have achieved remarkable success in image and video generation, yet the high computational cost of iterative sampling remains a critical bottleneck for practical deployment. Feature caching has emerged as a promising acceleration paradigm by reusing or predicting intermediate featur…

• RadioVIL: Anomaly-Aware Diffusion Models for Radio Map Inpainting and Zero-Shot Vehicle Localization

  Ruixin Zhao, Xiucheng Wang, Qiming Zhang, Nan Cheng, Ruijin Sun, Conghao Zhou · 18 de agosto de 2026 · Advanced Neural Network Applications

  High-precision radio map construction is essential for emerging 6G Integrated Sensing and Communication (ISAC) applications, including digital twins and intelligent transportation. However, existing deep learning methods predominantly treat this as a pure image completion task, resulting in over-smo…

• An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models

  Dengyang Jiang, Ruoyi Du, Zhennan Chen, Dongyang Liu, Zanyi Wang, Mingzhe Zheng, Xiangpeng Yang, Huanqia Cai, Aiming Hao, Yuming Jiang, Peng Gao, Harry Yang, Steven Hoi · 18 de agosto de 2026 · Generative Adversarial Networks and Image Synthesis

  This paper investigates an increasingly important topic in generative modeling: pixel-space diffusion models. Although numerous studies have explored this topic, most focus on small-scale or class-conditional settings. Consequently, a practical recipe for training pixel-space models that rival or ex…

• Revisiting Classifier-Free Guidance Methods in Latent Diffusion Models

  Artem Sergievskii, Artyom Turevich, Sergey Kastryulin · 18 de agosto de 2026 · Generative Adversarial Networks and Image Synthesis

  Inference-time quality-enhancement methods are an effective and widely adopted means of improving diffusion models without expensive retraining. We study a family of training-free techniques conceptually rooted in Classifier-Free Guidance (CFG), most of which were originally proposed on older U-Net …

• Offline Deep Q* Estimation with Diffusion Models

  Xiaohong Chen, Yuling Jiao, Lican Kang, Jerry Zhijian Yang, Chen Zhong · 17 de agosto de 2026 · Reinforcement Learning in Robotics

  In offline RL, estimating the optimal action-value function $Q^*$ can be formulated as solving the optimal Bellman equation based solely on offline observations. A fundamental challenge is that the reward function and transition kernel are unknown, so the optimal Bellman operator is not directly obs…

• VoiceDesigner: Text-to-Voice Generation and Editing via Unified Diffusion Modeling and Data Augmentation

  Jiarui Hai, Karan Thakkar, Ke Chen, Yunyun Wang, Jiaqi Su, Rithesh Kumar, Mounya Elhilali, Zeyu Jin · 17 de agosto de 2026 · Speech Recognition and Synthesis

  Recent breakthroughs in generative models have made text-to-voice generation (TTV) possible, enabling the synthesis of speech directly from textual voice descriptions. However, existing systems face two key challenges. First, they struggle to generate a diverse range of voices, spanning real-world h…

• Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space View

  Yixian Xu, Yuanrui Zhang, Shengjie Luo, Liwei Wang, Di He · 17 de agosto de 2026 · Generative Adversarial Networks and Image Synthesis

  Reinforcement learning (RL) post-training provides a direct way to align diffusion models with human preferences and task-specific rewards. However, current RL algorithms for diffusion models remain fragmented: reverse-trajectory methods rely on discretized likelihood ratios, whereas forward-matchin…

• Secret-Stego Dissimilarity as a Design Axis: Invertible Coverless Image Steganography with Diffusion Models

  Hongxin Xu, Jianping Mei, Can Wang, Defang Chen · 17 de agosto de 2026 · Generative Adversarial Networks and Image Synthesis

  Coverless image steganography (CIS) synthesizes a stego image rather than modifying an existing cover image, enabling authorized recipients to reconstruct the original secret image from the stego. Existing diffusion-based CIS methods can generate natural-looking stego images but preserve substantial…

• HPSD: Hybrid-Policy Self-Distillation for Text-Image-to-Video Diffusion Models

  Jiazi Bu, Pengyang Ling, Yujie Zhou, Yibin Wang, Yuhang Zang, Xuanlang Dai, Shengyuan Ding, Tianyi Wei, Xiaohang Zhan, Jiaqi Wang, Tong Wu, Dahua Lin, Xingang Pan · 14 de agosto de 2026 · Generative Adversarial Networks and Image Synthesis

  Text-Image-to-Video (TI2V) models are an emerging unified architecture, where a single model simultaneously supports text-to-video (T2V) and image-to-video (I2V) generation. Given a high-quality first frame or a detailed textual prompt, TI2V models unlock substantially better visual quality than the…

• Through Van Gogh's Eyes: Global Style Transfer with Diffusion Model

  Jeongha Lee, Yujin Kim, Ghazanfar Ali, Suhyun Kim, Jae-In Hwang · 13 de agosto de 2026 · Generative Adversarial Networks and Image Synthesis

  Artistic image synthesis aims to recreate the expressive visual identity of a target artist, yet existing methods often fail to capture an artist's global style. Conventional style transfer methods transfer the style of one or a few reference artworks to a content image in a One-to-One manner, makin…

• Fingerprinting Text-to-Image Diffusion Models via Collapsed Generation

  Yuanmin Huang, Chen Chen, Geng Hong, Xiaoyu You, Hui Xue, Zhenxing Qian, Mi Zhang, Min Yang · 13 de agosto de 2026 · Generative Adversarial Networks and Image Synthesis

  Proprietary text-to-image diffusion models are increasingly distributed as hosted services and downloadable checkpoints, making their intellectual property (IP) protection an increasingly critical concern when model leakage, copying, or unauthorized fine-tuning is disputed. In this work, we present …

• Demystifying Adversarial Robustness in Diffusion Models: Compression, Randomness, and Geometry

  Liu Yuezhang, Xue-Xin Wei · 12 de agosto de 2026 · Adversarial Robustness in Machine Learning

  Recent studies suggest that diffusion models significantly improve the empirical adversarial robustness of deep neural network models. While intuitive explanations have been proposed, the mechanisms underlying diffusion-based robustness remain largely unclear. This work aims to demystify how diffusi…

• DiffSafeMerge: Mitigating Backdoor Inheritance in Diffusion Model Merging

  Jiayang Zhang, Ji Guo, Jiachen Li, Wenshu Fan, Wenbo Jiang · 11 de agosto de 2026 · Generative Adversarial Networks and Image Synthesis

  Unconditional diffusion checkpoint merging assumes benign sources, yet a compromised public checkpoint can transfer a dormant backdoor while clean generation appears normal. Mitigation is difficult without knowing the compromised source, trigger, or target, and broad sanitization may degrade image q…

• eBIRD: Event-based Intensity Image Reconstruction Using Controllable Diffusion Models

  Ignacio Bugueno-Cordova, Fabian Valderrama, Rodrigo Verschae · 11 de agosto de 2026 · Advanced Memory and Neural Computing

  Intensity-image reconstruction from event streams remains a challenging problem due to the binary, sparse, and asynchronous nature of event data. This work proposes eBIRD, an event-guided reconstruction framework that combines a DDPM with ControlNet-based conditioning. We analyze generic and special…

• A Mean-Field Framework for Inference-Time Distributional Control of Diffusion Models

  Samuel Howard, Nikolas N\"usken · 11 de agosto de 2026 · Markov Chains and Monte Carlo Methods

  Diffusion models are increasingly used as controllable samplers, whose generations can be steered at inference time according to a chosen reward function. While such rewards are typically defined on individual samples, for many applications it is desirable to steer according to distribution-level re…

• DeepFreqMark: End-To-End Learnable Frequency-Domain Watermarking with Spherical Attack Simulation for Latent Diffusion Models

  Chen-Hsiu Huang, Mario K\"oppen, Ja-Ling Wu · 11 de agosto de 2026 · Advanced Steganography and Watermarking Techniques

  The proliferation of AI-generated images produced by Latent Diffusion Models (LDMs) has raised critical concerns regarding copyright infringement and misinformation. Although existing frequency-domain watermarking methods embed handcrafted geometric patterns into the initial latent noise prior to ge…

• PAST: Prompt-Adaptive Sampling Termination for Efficient Diffusion Model

  Renye Yan, Jikang Cheng, You Wu, Wei Peng, Zongwei Wang, Ling Liang, Yimao Cai · 10 de agosto de 2026 · Generative Adversarial Networks and Image Synthesis

  While diffusion models have made significant progress in text-to-image tasks, they still exhibit limitations when directly optimizing downstream objectives. Although Reinforcement Learning (RL) enables targeted optimization, existing methods are generally constrained by low-efficiency fine-tuning an…

• Explore or Converge? Stage-Guided Per-Step Optimization for Diffusion Models

  Renye Yan, Jikang Cheng, You Wu, Wei Peng, Zongwei Wang, Ling Liang, Yimao Cai · 10 de agosto de 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion models have strong generative capabilities. However, their maximum likelihood training objective only focuses on reconstructing the data distribution, making it difficult to align with specific preferences. Reinforcement learning (RL) for preference alignment in diffusion models is promisi…

• Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions

  Iskander Azangulov, George Deligiannidis, Judith Rousseau · 10 de agosto de 2026 · Advanced Mathematical Modeling in Engineering

  Denoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions and are widely used for image, audio, and video generation as well as many more applications in science and beyond. The \textit{manifold hypo…

• Quantum Generative Diffusion Model: A Fully Quantum-Mechanical Model for Generating Quantum State Ensemble

  Chuangtao Chen, Qinglin Zhao, MengChu Zhou, Zhimin He, Zhili Sun, Haozhen Situ · 10 de agosto de 2026 · Quantum Computing Algorithms and Architecture

  Mixed quantum states are the native description of many physically important quantum systems, making their generation a fundamental task in quantum information processing. However, constructing a diffusion process that generates density operators while keeping every reverse step physically valid rem…

• MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation

  Youjun Zhao, Alex Warren, Gary K. L. Tam, Rynson W. H. Lau · 10 de agosto de 2026 · Generative Adversarial Networks and Image Synthesis

  Recent advances in video diffusion models (VDMs) have enabled high-fidelity video synthesis. However, generating mirror reflections remains challenging because the content within a mirror must remain consistent with the surrounding scene. Existing VDMs are not specifically designed to model scene-to…

• Multi Codec Discrete Diffusion Model for Text Guided Speech Inpainting and Editing

  Iftach Shoham, Tali Dror, Oren Gal, Haim Permuter, Gilad Katz, Eliya Nachmani · 10 de agosto de 2026 · Speech Recognition and Synthesis

  Speech recordings often contain missing, corrupted, or incorrect regions that must be reconstructed or modified without re-synthesizing the entire utterance. Speech inpainting restores missing segments, whereas speech editing replaces spoken content according to an edited transcript. Both tasks requ…

• Diff-VF: Training-free High-quality Long Video Generation via Diffusion Model

  Haoning Yang, Xinyuan Chen, Yaohui Wang, Guo Lu · 7 de agosto de 2026 · Generative Adversarial Networks and Image Synthesis

  Recently, diffusion models have made great progress in video generation. However, most existing video diffusion models are trained with short videos, and degrade when extrapolated to long videos, struggling to maintain long-range temporal coherence while retaining diverse motions. To generate consis…