图像生成

Moment- and Power-Spectrum-Based Gaussianity Regularization for Text-to-Image Models

Jisung Hwang, Jaihoon Kim, Minhyuk Sung

机构 * KAIST（韩国科学技术院） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Comments Accepted to NeurIPS 2025

Erased or Dormant? Rethinking Concept Erasure Through Reversibility

Ping Liu, Chi Zhang

机构 * Department of Computer Science University of Nevada Reno（计算机科学系内华达大学拉斯维加斯分校） ； Department of Mathematics National University of Singapore（数学系新加坡国立大学） 纠错

专题命中 文生图 ：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments Dr. Chi Zhang is the corresponding author

UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets

Pengyu Wang, Shaojun Zhou, Chenkun Tan, Xinghao Wang, Wei Huang, Zhen Ye, Zhaowei Li, Botian Jiang, Dong Zhang, Xipeng Qiu

机构 * Fudan University（复旦大学） 纠错

专题命中 文生图 ：text-to-image(abstract)；image synthesis(abstract)

Comments Accepted by Findings of EMNLP2025

Chain-of-Thought Re-ranking for Image Retrieval Tasks

Shangrong Wu, Yanghong Zhou, Yang Chen, Feng Zhang, P. Y. Mok

专题命中 文生图 ：text-to-image(abstract)；分类 cs.CV

MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks

Mingsong Li, Lin Liu, Hongjun Wang, Haoxing Chen, Xijun Gu, Shizhan Liu, Dong Gong, Junbo Zhao, Zhenzhong Lan, Jianguo Li

机构 * University of New South Wales（新南威尔士大学） ； The University of Hong Kong（香港大学） ； Zhejiang University（浙江大学） ； Westlake University（西湖大学） 纠错

专题命中 图像编辑 ：image editing(title,abstract)；分类 cs.CV

Style Transfer with Diffusion Models for Synthetic-to-Real Domain Adaptation

Estelle Chigot, Dennis G. Wilson, Meriem Ghrib, Thomas Oberlin

机构 * ISAE-Supaero, University of Toulouse, France（ISAE-苏帕埃罗大学、图卢兹大学、法国） ； Airbus, France（空客公司、法国） 纠错

专题命中 图像编辑 ：diffusion(title,abstract)；分类 cs.CV

Comments Published in Computer Vision and Image Understanding, September 2025 (CVIU 2025)

End4: End-to-end Denoising Diffusion for Diffusion-Based Inpainting Detection

Fei Wang, Xuecheng Wu, Zheng Zhang, Danlei Huang, Yuheng Huang, Bo Wang

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

Radiology Report Conditional 3D CT Generation with Multi Encoder Latent diffusion Model

Sina Amirrajab, Zohaib Salahuddin, Sheng Kuang, Henry C. Woodruff, Philippe Lambin

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

OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers

Ziqiao Peng, Jiwen Liu, Haoxian Zhang, Xiaoqiang Liu, Songlin Tang, Pengfei Wan, Di Zhang, Hongyan Liu, Jun He

机构 * Renmin University of China（中国人民大学） ； Kling Team, Kuaishou Technology（快手科技 Kling 团队） ； Tsinghua University（清华大学） 纠错

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

Comments Accepted as NeurIPS 2025 spotlight

Lightweight and Accurate Multi-View Stereo with Confidence-Aware Diffusion Model

Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys

机构 * Department of Computer Science, ETH Zurich（苏黎世联邦理工学院计算机科学系） ； College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算机科学与数据科学学院） ； Center for Frontier AI Research, Institute of High Performance Computing, A*STAR（A*STAR前沿人工智能研究中心，高性能计算研究所） ； Microsoft, Zurich（微软（瑞士）） 纠错

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

Comments Accepted to IEEE T-PAMI 2025. Code: https://github.com/cvg/diffmvs

Data Augmentation via Latent Diffusion Models for Detecting Smell-Related Objects in Historical Artworks

Ahmed Sheta, Mathias Zinnen, Aline Sindel, Andreas Maier, Vincent Christlein

机构 * Pattern Recognition Lab, Friedrich-Alexander Universität Erlangen-Nürnberg, Germany（模式识别实验室，埃尔朗根-纽伦堡 Friedrich-Alexander 大学） 纠错

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

Comments Appeared at the 4th International Workshop on Fine Art Pattern Extraction and Recognition (FAPER 2025), in conjunction with ICIAP 2025; proceedings forthcoming in ICIAP 2025 Workshops (LNCS, Springer)

Adaptive and Iterative Point Cloud Denoising with Score-Based Diffusion Model

Zhaonan Wang, Manyi Li, ShiQing Xin, Changhe Tu

机构 * Shandong University（山东大学） 纠错

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

Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration

Junyuan Deng, Wei Yin, Xiaoyang Guo, Qian Zhang, Xiaotao Hu, Weiqiang Ren, Xiao-Xiao Long, Ping Tan

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学） ； Horizon Robotics ； Nanjing University（南京大学） 纠错

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

Conditional Prior-based Non-stationary Channel Estimation Using Accelerated Diffusion Models

Muhammad Ahmed Mohsin, Ahsan Bilal, Muhammad Umer, Asad Aali, Muhammad Ali Jamshed, Dean F. Hougen, John M. Cioffi

专题命中 扩散模型 ：diffusion(title,abstract)

Comments ICASSP 2026

AnoF-Diff: One-Step Diffusion-Based Anomaly Detection for Forceful Tool Use

Yating Lin, Zixuan Huang, Fan Yang, Dmitry Berenson

机构 * University of Michigan（密歇根大学） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)

A Novel Task-Driven Diffusion-Based Policy with Affordance Learning for Generalizable Manipulation of Articulated Objects

Hao Zhang, Zhen Kan, Weiwei Shang, Yongduan Song

机构 * Department of Automation at the University of Science and Technology of China（中国科学技术大学自动化系） ； School of Automation, Chongqing University（重庆大学自动化学院） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)

Comments Accepted by IEEE/ASME Transactions on Mechatronics

Hydrodynamic Attraction and Hindered Diffusion Govern First-passage Times of Swimming Microorganisms

Yanis Baouche, Magali Le Goff, Thomas Franosch, Christina Kurzthaler

专题命中 扩散模型 ：diffusion(title,abstract)

Diffusion-Based Unsupervised Audio-Visual Speech Separation in Noisy Environments with Noise Prior

Yochai Yemini, Rami Ben-Ari, Sharon Gannot, Ethan Fetaya

机构 * Faculty of Engineering, Bar-Ilan University（巴伊兰大学工程学院） ； OriginAI 纠错

专题命中 扩散模型 ：diffusion(title,abstract)

D4PM: A Dual-branch Driven Denoising Diffusion Probabilistic Model with Joint Posterior Diffusion Sampling for EEG Artifacts Removal

Feixue Shao, Xueyu Liu, Yongfei Wu, Jianbo Lu, Guiying Yan, Weihua Yang

专题命中 扩散模型 ：diffusion(title,abstract)

Controllable Surface Diffusion Generative Model for Neurodevelopmental Trajectories

Zhenshan Xie, Levente Baljer, M. Jorge Cardoso, Emma Robinson

机构 * Research Department of Biomedical Computing, School of Biomedical Engineering & Imaging Sciences, King’s College London（生物医学计算研究部，生物医学工程与成像科学学院，伦敦国王学院） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)

Robust Reinforcement Learning under Diffusion Models for Data with Jumps

Chenyang Jiang, Donggyu Kim, Alejandra Quintos, Yazhen Wang

机构 * Department of Statistics, University of Wisconsin-Madison（统计学系，威斯康星大学麦迪逊分校） ； Department of Economics, University of California, Riverside（经济学系，加州大学河滨分校） 纠错

专题命中 扩散模型 ：diffusion(title)

Learning Mechanistic Subtypes of Neurodegeneration with a Physics-Informed Variational Autoencoder Mixture Model

Sanduni Pinnawala, Annabelle Hartanto, Ivor J. A. Simpson, Peter A. Wijeratne

机构 * Sussex AI Centre, School of Engineering and Informatics, University of Sussex, UK（Sussex大学人工智能中心，工程与信息学学院，英国） 纠错

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

Comments 13 pages, 5 figures, accepted at SASHIMI workshop, MICCAI 2025

[Re] Improving Interpretation Faithfulness for Vision Transformers

Izabela Kurek, Wojciech Trejter, Stipe Frkovic, Andro Erdelez

机构 * University of Amsterdam（阿姆斯特丹大学） 纠错

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

Comments 13 pages article, 29 pdf pages, 19 figures, MLRC. Transactions on Machine Learning Research (2025)

Unveiling TeV halos among unidentified extended TeV sources

Michela Rigoselli, Sarah Recchia, Alberto Bonollo, Silvia Crestan, Giada Peron, Andrea Giuliani, Sandro Mereghetti

专题命中 扩散模型 ：diffusion(abstract)

Comments Presented at the 39th International Cosmic Ray Conference (ICRC 2025), 2025

Finite Volumes for a dissipative free boundary problem

Clément Cancès, Claire Chainais-Hillairet, Amélie Dupouy

专题命中 扩散模型 ：diffusion(abstract)

CollabVLA: Self-Reflective Vision-Language-Action Model Dreaming Together with Human

Nan Sun, Yongchang Li, Chenxu Wang, Huiying Li, Huaping Liu

机构 * Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学） 纠错

专题命中 扩散模型 ：diffusion(abstract)

Comments 8 pages, 5 figures, 3 tables

Towards Pre-trained Graph Condensation via Optimal Transport

Yeyu Yan, Shuai Zheng, Wenjun Hui, Xiangkai Zhu, Dong Chen, Zhenfeng Zhu, Yao Zhao, Kunlun He

机构 * Beijing Jiaotong University（北京交通大学） ； Jinan University（济南大学） ； Chinese PLA General Hospital（中国人民解放军总医院） 纠错

专题命中 扩散模型 ：diffusion(abstract)

Radiolunadiff: Estimation of wireless network signal strength in lunar terrain

Paolo Torrado, Anders Pearson, Jason Klein, Alexander Moscibroda, Joshua Smith

专题命中 扩散模型 ：diffusion(abstract)

Electricity in international comparison -- Future technologies in power generation

Axel Kleidon, Harald Lesch, Russ Conser

专题命中 扩散模型 ：diffusion(abstract)

Comments 8 pages, 4 figures, manuscript in press in Physik in unserer Zeit (in German). DOI will be linked once manuscript is published

FlowDrive: Energy Flow Field for End-to-End Autonomous Driving

Hao Jiang, Zhipeng Zhang, Yu Gao, Zhigang Sun, Yiru Wang, Yuwen Heng, Shuo Wang, Jinhao Chai, Zhuo Chen, Hao Zhao, Hao Sun, Xi Zhang, Anqing Jiang, Chuan Hu

机构 * Shanghai Jiao Tong University（上海交通大学） ； Bosch Corporate Research, Shanghai, China（博世股份有限公司上海研究院） ； AIR, Tsinghua University（清华大学人工智能研究院） ； Shanghai University, Shanghai, China（上海大学） 纠错

专题命中 扩散模型 ：diffusion(abstract)