arXivDaily arXiv每日学术速递 周一至周五更新

视觉与机器人

图像生成

图像生成、文生图、图像编辑、扩散模型和可控生成。

2025-10-21 至 2025-10-21 共收录 115 信号源:cs.CV, cs.GR, cs.MM

1. 扩散模型 83 篇

2510.16125 2025-10-21 astro-ph.GA astro-ph.HE 78%

Effective cosmic ray diffusion in multiphase galactic environments

Timon Thomas, Christoph Pfrommer, Rüdiger Pakmor, Rouven Lemmerz, Mohamad Shalaby

专题命中 扩散模型 :diffusion(title,abstract)

Comments 16 pages, 11 figures, comments are welcome!

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.16037 2025-10-21 cs.CR cs.AI cs.LG 78%

Membership Inference over Diffusion-models-based Synthetic Tabular Data

Peini Cheng, Amir Bahmani

机构 * University of Alberta(阿尔伯塔大学)

专题命中 扩散模型 :diffusion(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.15895 2025-10-21 cs.HC cs.AI cs.SD 78%

BREATH: A Bio-Radar Embodied Agent for Tonal and Human-Aware Diffusion Music Generation

Yunzhe Wang, Xinyu Tang, Zhixun Huang, Xiaolong Yue, Yuxin Zeng

专题命中 扩散模型 :diffusion(title,abstract)

Comments Accepted by LLM4Music @ ISMIR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06303 2025-10-21 cs.LG cs.AI 78%

SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation

Shuang Cheng, Yihan Bian, Dawei Liu, Linfeng Zhang, Qian Yao, Zhongbo Tian, Wenhai Wang, Qipeng Guo, Kai Chen, Biqing Qi, Bowen Zhou

机构 * Shanghai AI Laboratory(上海人工智能实验室) Zhejiang University(浙江大学) University of Maryland, College Park(马里兰大学 College Park 分校) Shanghai Jiao Tong University(上海交通大学) Tsinghua University(清华大学)

专题命中 扩散模型 :diffusion(title,abstract)

Comments Technical report. 40 pages, Inference speedup analysis added

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.10348 2025-10-21 cond-mat.mtrl-sci 78%

A collapsed interface approach to resolve grain boundaries in finite element simulations of polycrystalline diffusion

Lena Scholz, Yongliang Ou, Blazej Grabowski, Felix Fritzen

专题命中 扩散模型 :diffusion(title,abstract)

Comments Updated to include a more general presentation of the results and to expand explanations for improved clarity and accessibility

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.05730 2025-10-21 cs.CY cs.AI 78%

Robust Optimization with Diffusion Models for Green Security

Lingkai Kong, Haichuan Wang, Yuqi Pan, Cheol Woo Kim, Mingxiao Song, Alayna Nguyen, Tonghan Wang, Haifeng Xu, Milind Tambe

机构 * Harvard University(哈佛大学) University of Chicago(芝加哥大学)

专题命中 扩散模型 :diffusion(title,abstract)

Comments UAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.09992 2025-10-21 cs.CL cs.LG 78%

Large Language Diffusion Models

Shen Nie, Fengqi Zhu, Zebin You, Xiaolu Zhang, Jingyang Ou, Jun Hu, Jun Zhou, Yankai Lin, Ji-Rong Wen, Chongxuan Li

机构 * Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学人工智能学院) Beijing Key Laboratory of Research on Large Models and Intelligent Governance(北京大型模型与智能治理研究重点实验室) Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE(下一代智能搜索与推荐工程研究中心) Ant Group(蚂蚁集团)

专题命中 扩散模型 :diffusion(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.09890 2025-10-21 cs.LG 78%

Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion

Vinh Tong, Hoang Trung-Dung, Anji Liu, Guy Van den Broeck, Mathias Niepert

机构 * University of Stuttgart(斯图加特大学) IMPRS-IS(马克斯·普朗克研究所-人工智能与系统科学) UCLA(加州大学洛杉矶分校) University of Bern(伯尔尼大学) National University of Singapore(新加坡国立大学)

专题命中 扩散模型 :diffusion(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.01838 2025-10-21 hep-ph 78%

Aspects of holographic Langevin diffusion in the presence of anisotropic magnetic field

Qi Zhou, Ben-Wei Zhang

专题命中 扩散模型 :diffusion(title,abstract)

Comments 9 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.18012 2025-10-21 cs.LG cs.AI 78%

Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints

Lingkai Kong, Yuanqi Du, Wenhao Mu, Kirill Neklyudov, Valentin De Bortoli, Dongxia Wu, Haorui Wang, Aaron Ferber, Yi-An Ma, Carla P. Gomes, Chao Zhang

机构 * Georgia Tech(佐治亚理工学院) Cornell University(康奈尔大学) Université de Montréal(蒙特利尔大学) Mila(Mila研究院) ENS, CNRS, PSL University(巴黎高等师范学院、国家科学研究中心、巴黎-萨克勒大学) UCSD(加州大学圣地亚哥分校)

专题命中 扩散模型 :diffusion(title,abstract)

Comments AISTATS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.01737 2025-10-21 cs.CV 74%

HOI-Dyn: Learning Interaction Dynamics for Human-Object Motion Diffusion

Lin Wu, Zhixiang Chen, Jianglin Lan

机构 * James Watt School of Engineering University of Glasgow(詹姆斯·瓦特工程学院格拉斯哥大学) School of Computer Science University of Sheffield(计算机科学学院谢菲尔德大学)

专题命中 扩散模型 :diffusion(title);分类 cs.CV

Comments Accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.07908 2025-10-21 eess.AS 71%

Guitar Tone Morphing by Diffusion-based Model

Kuan-Yu Chen, Kuan-Lin Chen, Yu-Chieh Yu, Jian-Jiun Ding

专题命中 扩散模型 :diffusion(title)

Comments 5 pages, accepted to the APSIPA ASC 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.17486 2025-10-21 cs.CV cs.AI 70%

Unsupervised anomaly detection using Bayesian flow networks: application to brain FDG PET in the context of Alzheimer's disease

Hugues Roy, Reuben Dorent, Ninon Burgos

机构 * Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié Salpêtrière, F-75013, Paris, France(索邦大学,大脑研究所-巴黎脑研究所-ICM,CNRS,Inria,Inserm,AP-HP,皮蒂埃-萨拉普特里医院,法国巴黎) MIND Team, Inria Saclay, Université Paris-Saclay, Palaiseau, France(MIND团队,Inria萨克利,巴黎-萨克利大学,帕莱赛,法国)

专题命中 扩散模型 :image generation(abstract);diffusion(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17786 2025-10-21 cs.LG 67%

Inference-Time Compute Scaling For Flow Matching

Adam Stecklov, Noah El Rimawi-Fine, Mathieu Blanchette

机构 * McGill University(麦吉尔大学) Mila – Quebec AI Institute(魁北克AI研究所)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.16136 2025-10-21 cs.CV cs.AI cs.GR 62%

GuideFlow3D: Optimization-Guided Rectified Flow For Appearance Transfer

Sayan Deb Sarkar, Sinisa Stekovic, Vincent Lepetit, Iro Armeni

机构 * Stanford University(斯坦福大学) ENPC, IP Paris(巴黎理工学院)

专题命中 扩散模型 :diffusion(abstract);分类 cs.CV、cs.GR

Comments NeurIPS 2025. Project Page: https://sayands.github.io/guideflow3d/

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17731 2025-10-21 cs.CV 57%

Can Image-To-Video Models Simulate Pedestrian Dynamics?

Aaron Appelle, Jerome P. Lynch

机构 * Duke University(杜克大学)

专题命中 扩散模型 :diffusion(abstract);分类 cs.CV

Comments Appeared in the ICML 2025 Workshop on Building Physically Plausible World Models, July 2025, https://physical-world-modeling.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17188 2025-10-21 cs.CV 57%

HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery

Vaibhav Rathore, Divyam Gupta, Biplab Banerjee

机构 * Indian Institute of Technology Bombay(印度理工学院孟买)

专题命中 扩散模型 :diffusion(abstract);分类 cs.CV

Comments Accpeted at NeurIPS (2025) Main Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.03621 2025-10-21 cs.CV 57%

DynVFX: Augmenting Real Videos with Dynamic Content

Danah Yatim, Rafail Fridman, Omer Bar-Tal, Tali Dekel

机构 * Weizmann Institute of Science(魏兹曼科学研究所)

专题命中 扩散模型 :diffusion(abstract);分类 cs.CV

Comments Project page: https://dynvfx.github.io

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.16321 2025-10-21 eess.IV cs.AI cs.CV cs.LG physics.med-ph 57%

Time-Embedded Algorithm Unrolling for Computational MRI

Junno Yun, Yaşar Utku Alçalar, Mehmet Akçakaya

专题命中 扩散模型 :diffusion(abstract);分类 cs.CV

Comments Neural Information Processing Systems (NeurIPS), 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.16118 2025-10-21 cs.CV 57%

ObjectTransforms for Uncertainty Quantification and Reduction in Vision-Based Perception for Autonomous Vehicles

Nishad Sahu, Shounak Sural, Aditya Satish Patil, Ragunathan, Rajkumar

机构 * Carnegie Mellon University(卡内基梅隆大学) University Of Minnesota(明尼苏达大学)

专题命中 扩散模型 :diffusion(abstract);分类 cs.CV

Comments Accepted at International Conference on Computer Vision (ICCV) 2025 Workshops

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.21152 2025-10-21 cs.CV 57%

Geometry and Perception Guided Gaussians for Multiview-consistent 3D Generation from a Single Image

Pufan Li, Bi'an Du, Wei Hu

机构 * Wangxuan Institute of Computer Technology, Peking University(北京大学王轩计算机技术研究所)

专题命中 扩散模型 :diffusion(abstract);分类 cs.CV

Comments 10 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.10809 2025-10-21 cs.CV 57%

GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDR

Christophe Bolduc, Yannick Hold-Geoffroy, Zhixin Shu, Jean-François Lalonde

机构 * Université Laval(拉瓦尔大学) Adobe(Adobe公司)

专题命中 扩散模型 :diffusion(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.17041 2025-10-21 cs.CV cs.AI cs.LG 57%

Free$^2$Guide: Training-Free Text-to-Video Alignment using Image LVLM

Jaemin Kim, Bryan Sangwoo Kim, Jong Chul Ye

机构 * Graduate School of AI, KAIST(人工智能研究生院,韩国科学技术院)

专题命中 扩散模型 :diffusion(abstract);分类 cs.CV

Comments ICCV 2025 accepted

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17648 2025-10-21 math.ST stat.TH 50%

Wild regenerative block bootstrap for Harris recurrent Markov chains

Kyuseong Choi, Gabriella Ciolek

专题命中 扩散模型 :diffusion(abstract)

Comments 47 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17608 2025-10-21 stat.ML cs.LG math.ST stat.TH 50%

Non-asymptotic error bounds for probability flow ODEs under weak log-concavity

Gitte Kremling, Francesco Iafrate, Mahsa Taheri, Johannes Lederer

专题命中 扩散模型 :diffusion(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17443 2025-10-21 physics.chem-ph 50%

Ionic current rectification under concentration gradients and its application in evaluating surface charge properties of micropores

Long Ma, Hongwen Zhang, Bowen Ai, Jiakun Zhuang, Guanghua Du, Yinghua Qiu

专题命中 扩散模型 :diffusion(abstract)

Comments 23 pages, 5 figures

Journal ref The Journal of Chemical Physics, 2025, 162 (9): 094704

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17441 2025-10-21 cond-mat.mtrl-sci cond-mat.mes-hall 50%

Electrical properties of PbS films doped with iodine by chemical bath deposition

T. B. Charikova, A. Yu. Pavlova, M. R. Popov, A. V. Pozdin, L. N. Maskaeva

专题命中 扩散模型 :diffusion(abstract)

Comments 15 pages, 7 figures, 2 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.16999 2025-10-21 nlin.CD 50%

The subtlety of the outermost stellarator magnetic surface

Alkesh Punjabi, Allen H. Boozer

专题命中 扩散模型 :diffusion(abstract)

Comments 22 pages, 15 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.16995 2025-10-21 eess.AS 50%

Adaptive Deterministic Flow Matching for Target Speaker Extraction

Tsun-An Hsieh, Minje Kim

专题命中 扩散模型 :diffusion(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.16990 2025-10-21 cs.LG 50%

Graph4MM: Weaving Multimodal Learning with Structural Information

Xuying Ning, Dongqi Fu, Tianxin Wei, Wujiang Xu, Jingrui He

机构 * University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) Meta AI Rutgers University(罗格斯大学)

专题命中 扩散模型 :diffusion(abstract)

Comments ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏