图像生成 - arXivDaily 专题

2510.08488 2025-10-10 physics.geo-ph 82%

Diffusion-Based Probabilistic Modeling for Hourly Streamflow Prediction and Assimilation

Wencong Yang, Haoyu Ji, Leo Lonzarich, Yalan Song, Chaopeng Shen

专题命中扩散模型：diffusion(title,abstract)；inpainting(abstract)

2405.17068 2025-10-10 cs.LG cs.NA math.NA stat.ML 82%

The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models

Saravanan Kandasamy, Dheeraj Nagaraj

机构 * Cornell University（康奈尔大学）； Google DeepMind（谷歌DeepMind）

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)

Comments "One often meets his destiny on the road he takes to avoid it" - Master Oogway. My destiny seems to be to write triangle inequalities for the rest of my life

2510.04153 2025-10-07 cs.CR cs.LG 82%

ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation

Haoqi Wu, Wei Dai, Ming Xu, Li Wang, Qiang Yan

机构 * TikTok Inc.（TikTok公司）； National University of Singapore（新加坡国立大学）

专题命中扩散模型：image generation(title,abstract)；diffusion(abstract)

Comments Accepted by NeurIPS 2025

2501.09253 2025-10-07 cs.DC 82%

PATCHEDSERVE: A Patch Management Framework for SLO-Optimized Hybrid Resolution Diffusion Serving

Desen Sun, Zepeng Zhao, Yuke Wang

专题命中扩散模型：diffusion(title,abstract)；text-to-image(abstract)

2510.02063 2025-10-03 eess.IV 82%

MSRepaint: Multiple Sclerosis Repaint with Conditional Denoising Diffusion Implicit Model for Bidirectional Lesion Filling and Synthesis

Jinwei Zhang, Lianrui Zuo, Yihao Liu, Hang Zhang, Samuel W. Remedios, Bennett A. Landman, Peter A. Calabresi, Shiv Saidha, Scott D. Newsome, Dzung L. Pham, Jerry L. Prince, Ellen M. Mowry, Aaron Carass

专题命中扩散模型：diffusion(title,abstract)；inpainting(abstract)

2510.01329 2025-10-03 stat.ML cs.LG 82%

Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling

Huangjie Zheng, Shansan Gong, Ruixiang Zhang, Tianrong Chen, Jiatao Gu, Mingyuan Zhou, Navdeep Jaitly, Yizhe Zhang

机构 * Apple（苹果公司）

专题命中扩散模型：diffusion(title,abstract)；image synthesis(abstract)

2510.00778 2025-10-02 cs.AI 82%

DIA: The Adversarial Exposure of Deterministic Inversion in Diffusion Models

Seunghoo Hong, Geonho Son, Juhun Lee, Simon S. Woo

专题命中扩散模型：diffusion(title,abstract)；image editing(abstract)

Comments ICCV2025

2509.21262 2025-09-30 cs.CL 82%

Un-Doubling Diffusion: LLM-guided Disambiguation of Homonym Duplication

Evgeny Kaskov, Elizaveta Petrova, Petr Surovtsev, Anna Kostikova, Ilya Mistiurin, Alexander Kapitanov, Alexander Nagaev

专题命中扩散模型：diffusion(title,abstract)；text-to-image(abstract)

2509.20109 2025-09-25 cs.RO cs.AI cs.CL 82%

Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving

Pengxiang Li, Yinan Zheng, Yue Wang, Huimin Wang, Hang Zhao, Jingjing Liu, Xianyuan Zhan, Kun Zhan, Xianpeng Lang

机构 * LiAuto ； Tsinghua University（清华大学）

专题命中扩散模型：diffusion(title,abstract)；inpainting(abstract)

2403.06279 2025-09-25 math.OC cs.LG 82%

Fine-tuning of diffusion models via stochastic control: entropy regularization and beyond

Wenpin Tang, Fuzhong Zhou

机构 * Department of Industrial Engineering and Operations Research, Columbia University（工业工程与运筹学系，哥伦比亚大学）

专题命中扩散模型：diffusion(title,abstract)；text-to-image(abstract)

Comments 17 pages

2509.17250 2025-09-23 cs.LG eess.SP 82%

Graph Signal Generative Diffusion Models

Yigit Berkay Uslu, Samar Hadou, Sergio Rozada, Shirin Saeedi Bidokhti, Alejandro Ribeiro

机构 * Dept. of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA（电气与系统工程系，宾夕法尼亚大学）； Dept. of Signal Processing and Communications, King Juan Carlos University, Madrid, Spain（信号处理与通信系，国王胡安·卡洛斯大学）

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)

Comments Submitted to 2026 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026)

2507.02598 2025-09-17 cs.AR cs.AI 82%

AC-Refiner: Efficient Arithmetic Circuit Optimization Using Conditional Diffusion Models

Chenhao Xue, Kezhi Li, Jiaxing Zhang, Yi Ren, Zhengyuan Shi, Chen Zhang, Yibo Lin, Lining Zhang, Qiang Xu, Guangyu Sun

机构 * School of Integrated Circuits, Peking University（集成电路学院，北京大学）； Department of Computer Science and Engineering, The Chinese University of Hong Kong（计算机科学与工程系，香港中文大学）； School of Software and Microelectronics, Peking University（软件与微电子学院，北京大学）； Shanghai Jiao Tong University（上海交通大学）； Institute of Electronic Design Automation, Peking University（电子设计自动化研究所，北京大学）； Beijing Advanced Innovation Center for Integrated Circuits（北京集成电路先进创新中心）； School of Electronic and Computer Engineering, Peking University（电子与计算机工程学院，北京大学）； National Center of Technology Innovation for EDA（EDA技术创新国家中心）

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)

Comments 8 pages, 12 figures, to appear in ASP-DAC'26

2509.05107 2025-09-08 q-fin.TR 82%

Painting the market: generative diffusion models for financial limit order book simulation and forecasting

Alfred Backhouse, Kang Li, Jakob Foerster, Anisoara Calinescu, Stefan Zohren

专题命中扩散模型：diffusion(title,abstract)；inpainting(abstract)

Comments Submitted to ICAIF

2509.03341 2025-09-04 cs.LG cs.AI 82%

On the MIA Vulnerability Gap Between Private GANs and Diffusion Models

Ilana Sebag, Jean-Yves Franceschi, Alain Rakotomamonjy, Alexandre Allauzen, Jamal Atif

专题命中扩散模型：diffusion(title,abstract)；image synthesis(abstract)

2509.02308 2025-09-03 cs.AI 82%

Exploring Diffusion Models for Generative Forecasting of Financial Charts

Taegyeong Lee, Jiwon Park, Kyunga Bang, Seunghyun Hwang, Ung-Jin Jang

机构 * FnGuide Inc.（FnGuide公司）； GenAI in Finance, MODULABS（金融领域生成式AI，MODULABS）； Department of Applied Data Science, Sungkyunkwan University（Sungkyunkwan大学应用数据科学系）

专题命中扩散模型：diffusion(title,abstract)；text-to-image(abstract)

2507.14507 2025-09-03 stat.ML cs.AI cs.LG 82%

Diffusion Models for Time Series Forecasting: A Survey

Chen Su, Zhengzhou Cai, Yuanhe Tian, Zhuochao Chang, Zihong Zheng, Yan Song

机构 * University of Science and Technology of China（中国科学技术大学）； Beijing University of Posts and Telecommunications（北京邮电大学）； University of Washington（华盛顿大学）

专题命中扩散模型：diffusion(title,abstract)；image synthesis(abstract)

2503.03007 2025-08-28 math.OC cs.LG math.PR stat.ML 82%

Benchmarking Diffusion Annealing-Based Bayesian Inverse Problem Solvers

Evan Scope Crafts, Umberto Villa

机构 * Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin（奥登计算工程与科学研究所，德克萨斯大学奥斯汀分校）； Dept of Biomedical Engineering, The University of Texas at Austin（生物医学工程系，德克萨斯大学奥斯汀分校）

专题命中扩散模型：diffusion(title,abstract)；inpainting(abstract)

Journal ref IEEE Open J. Signal Process. 6 (2025) 975-991

2508.17465 2025-08-26 cs.CY cs.AI 82%

Bias Amplification in Stable Diffusion's Representation of Stigma Through Skin Tones and Their Homogeneity

Kyra Wilson, Sourojit Ghosh, Aylin Caliskan

专题命中扩散模型：diffusion(title,abstract)；text-to-image(abstract)

Comments Published in Proceedings of the 2024 AAAI/ACM Conference on AI, Ethics, and Society; code available at https://github.com/kyrawilson/Image-Generation-Bias

2412.01528 2025-08-22 cs.AI 82%

CopyrightShield: Enhancing Diffusion Model Security against Copyright Infringement Attacks

Zhixiang Guo, Siyuan Liang, Aishan Liu, Dacheng Tao

机构 * Nanyang Technological University（南洋理工大学）； Beihang University（北航大学）

专题命中扩散模型：diffusion(title,abstract)；image synthesis(abstract)

2508.13077 2025-08-19 eess.IV cs.AI 82%

From Transthoracic to Transesophageal: Cross-Modality Generation using LoRA Diffusion

Emmanuel Oladokun, Yuxuan Ou, Anna Novikova, Daria Kulikova, Sarina Thomas, Jurica Šprem, Vicente Grau

机构 * University of Oxford GE HealthCare, Cardiovascular Ultrasound R\&D

专题命中扩散模型：diffusion(title,abstract)；image synthesis(abstract)

Comments MICCAI 2025; ASMUS

2508.12701 2025-08-19 eess.SY cs.SY 82%

Deadline-Aware Bandwidth Allocation for Semantic Generative Communication with Diffusion Models

Jinhyuk Choi, Jihong Park, Seungeun Oh, Seong-Lyun Kim

专题命中扩散模型：diffusion(title,abstract)；inpainting(abstract)

2508.12361 2025-08-19 cs.LG cs.AI math.ST stat.TH 82%

Navigating the Exploration-Exploitation Tradeoff in Inference-Time Scaling of Diffusion Models

Xun Su, Jianming Huang, Yang Yusen, Zhongxi Fang, Hiroyuki Kasai

专题命中扩散模型：diffusion(title,abstract)；text-to-image(abstract)

2409.04832 2025-08-12 cs.LG cs.AI math.OC 82%

Reward-Directed Score-Based Diffusion Models via q-Learning

Xuefeng Gao, Jiale Zha, Xun Yu Zhou

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)

2501.09014 2025-08-07 cs.SE cs.AI 82%

How Do Generative Models Draw a Software Engineer? A Case Study on Stable Diffusion Bias

Tosin Fadahunsi, Giordano d'Aloisio, Antinisca Di Marco, Federica Sarro

机构 * Department of Computer Science, University College London, London, UK（计算机科学系，伦敦大学学院，伦敦，英国）； Department of Information Engineering, Computer Science and Mathematics, University of L'Aquila, L'Aquila, Italy（信息工程、计算机科学与数学系，拉奎拉大学，拉奎拉，意大利）

专题命中扩散模型：diffusion(title,abstract)；text-to-image(abstract)

2507.06133 2025-07-28 cs.CE 82%

Bridging Sequential Deep Operator Network and Video Diffusion: Residual Refinement of Spatio-Temporal PDE Solutions

Jaewan Park, Farid Ahmed, Kazuma Kobayashi, Seid Koric, Syed Bahauddin Alam, Iwona Jasiuk, Diab Abueidda

专题命中扩散模型：diffusion(title,abstract)；inpainting(abstract)

2503.07677 2025-07-22 cs.LG cs.AI 82%

PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity

Kwanyoung Kim, Byeongsu Sim

机构 * Samsung Research（三星研究）

专题命中扩散模型：diffusion(title,abstract)；text-to-image(abstract)

Comments Camera ready version for ICCV 2025, 30 pages, 20 figures, project page : https://cubeyoung.github.io/pladis-proejct/

2507.10861 2025-07-16 cs.LG 82%

Visually grounded emotion regulation via diffusion models and user-driven reappraisal

Edoardo Pinzuti, Oliver Tüscher, André Ferreira Castro

机构 * Leibniz Institute for Resilience Research（莱比锡韧性研究所）； University Medicine Halle (Saale) of the Martin Luther University Halle-Wittenberg (MLU)（马尔堡-哈雷大学哈雷-萨勒医学院）； German Center for Mental Health (DZPG)（德国心理健康中心）； School of Life Sciences, Technical University of Munich（慕尼黑技术大学生命科学学院）

专题命中扩散模型：diffusion(title,abstract)；text-to-image(abstract)

2406.15213 2025-07-08 cs.LG cs.AI cs.CR 82%

Backdooring Bias ($B^2$) into Stable Diffusion Models

Ali Naseh, Jaechul Roh, Eugene Bagdasarian, Amir Houmansadr

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)

Comments Accepted to USENIX Security '25

2308.06405 2025-07-08 cs.CR 82%

White-box Membership Inference Attacks against Diffusion Models

Yan Pang, Tianhao Wang, Xuhui Kang, Mengdi Huai, Yang Zhang

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)

Journal ref Proceedings on Privacy Enhancing Technologies Symposium 2025 2 398-415

2304.04971 2025-06-26 cs.IR 82%

Diffusion Recommender Model

Wenjie Wang, Yiyan Xu, Fuli Feng, Xinyu Lin, Xiangnan He, Tat-Seng Chua

专题命中扩散模型：diffusion(title,abstract)；image synthesis(abstract)

Comments 10 pages, 7 figures, accepted for publication in SIGIR'23

1. 扩散模型 70196 篇

Diffusion-Based Probabilistic Modeling for Hourly Streamflow Prediction and Assimilation

The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models

ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation

PATCHEDSERVE: A Patch Management Framework for SLO-Optimized Hybrid Resolution Diffusion Serving

MSRepaint: Multiple Sclerosis Repaint with Conditional Denoising Diffusion Implicit Model for Bidirectional Lesion Filling and Synthesis

Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling

DIA: The Adversarial Exposure of Deterministic Inversion in Diffusion Models

Un-Doubling Diffusion: LLM-guided Disambiguation of Homonym Duplication

Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving

Fine-tuning of diffusion models via stochastic control: entropy regularization and beyond

Graph Signal Generative Diffusion Models

AC-Refiner: Efficient Arithmetic Circuit Optimization Using Conditional Diffusion Models

Painting the market: generative diffusion models for financial limit order book simulation and forecasting

On the MIA Vulnerability Gap Between Private GANs and Diffusion Models

Exploring Diffusion Models for Generative Forecasting of Financial Charts

Diffusion Models for Time Series Forecasting: A Survey

Benchmarking Diffusion Annealing-Based Bayesian Inverse Problem Solvers

Bias Amplification in Stable Diffusion's Representation of Stigma Through Skin Tones and Their Homogeneity

CopyrightShield: Enhancing Diffusion Model Security against Copyright Infringement Attacks

From Transthoracic to Transesophageal: Cross-Modality Generation using LoRA Diffusion

Deadline-Aware Bandwidth Allocation for Semantic Generative Communication with Diffusion Models

Navigating the Exploration-Exploitation Tradeoff in Inference-Time Scaling of Diffusion Models

Reward-Directed Score-Based Diffusion Models via q-Learning

How Do Generative Models Draw a Software Engineer? A Case Study on Stable Diffusion Bias

Bridging Sequential Deep Operator Network and Video Diffusion: Residual Refinement of Spatio-Temporal PDE Solutions

PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity

Visually grounded emotion regulation via diffusion models and user-driven reappraisal

Backdooring Bias ($B^2$) into Stable Diffusion Models

White-box Membership Inference Attacks against Diffusion Models

Diffusion Recommender Model