图像生成

Gradients: When Markets Meet Fine-tuning -- A Distributed Approach to Model Optimisation

Christopher Subia-Waud

机构 * Rayon Labs（Rayon实验室） 纠错

专题命中 扩散模型 ：diffusion(abstract)

Enhanced Dissipation via time-modulated velocity fields

Johannes Benthaus, Camilla Nobili

专题命中 扩散模型 ：diffusion(abstract)

Comments Minor edits. To appear in Evolution Equations and Control Theory

Journal ref Evolution Equations and Control Theory (2025)

Principled model selection for stochastic dynamics

Andonis Gerardos, Pierre Ronceray

专题命中 扩散模型 ：diffusion(abstract)

A Calderón type inverse problem for the active scalar equations with fractional dissipation

Li Li, Weinan Wang

专题命中 扩散模型 ：diffusion(abstract)

Impact of chirality on active Brownian particle: Exact moments in two and three dimensions

Anweshika Pattanayak, Amir Shee, Debasish Chaudhuri, Abhishek Chaudhuri

专题命中 扩散模型 ：diffusion(abstract)

Comments 27 pages, 8 figures

Journal ref New J. Phys. 26, 083024 (2024)

Asymptotic periodic solutions of differential equations with infinite delay

Nguyen Duc Huy, Le Anh Minh, Vu trong Luong, Nguyen Ngoc Vien

专题命中 扩散模型 ：diffusion(abstract)

Comments I need to revise certain sections of this paper

FetalFlex: Anatomy-Guided Diffusion Model for Flexible Control on Fetal Ultrasound Image Synthesis

Yaofei Duan, Tao Tan, Zhiyuan Zhu, Yuhao Huang, Yuanji Zhang, Rui Gao, Patrick Cheong-Iao Pang, Xinru Gao, Guowei Tao, Xiang Cong, Zhou Li, Lianying Liang, Guangzhi He, Linliang Yin, Xuedong Deng, Xin Yang, Dong Ni

机构 * organization= Faculty of Applied Sciences, Macao Polytechnic University , city= Macao , country= China ； organization= National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University , city= Shenzhen , state= Guangdong , country= China ； organization= Shenzhen RayShape Medical Technology Co., Ltd , city= Shenzhen , state= Guangdong , country= China ； organization= Department of Ultrasound, Shenzhen Guangming District People’s Hospital , city= Shenzhen , state= Guangdong , country= China ； organization= Jinan University , city= Guangzhou , state= Guangdong , country= China ； organization= Center for Medical Ultrasound, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Gusu School, Nanjing Medical University , city= Suzhou , state= Jiangsu , country= China ； organization= Medical Ultrasound Image Computing (MUSIC) Laboratory, Shenzhen University , city= Shenzhen , state= Guangdong , country= China ； organization= Qilu Hospital of Shandong University , city= Jinan , state= Shandong , country= China ； organization= Northwest Women \& Children Hospital , city= Xian , state= Shaanxi , country= China 纠错

专题命中 可控生成 ：diffusion(title)；image synthesis(title)；image generation(abstract)；分类 cs.CV

Comments 18 pages, 10 figures

DUViN: Diffusion-Based Underwater Visual Navigation via Knowledge-Transferred Depth Features

Jinghe Yang, Minh-Quan Le, Mingming Gong, Ye Pu

机构 * Department of Electrical and Electronic Engineering, The University of Melbourne, Australia（墨尔本大学电子与电气工程系） ； School of Mathematics and Statistics, The University of Melbourne, Australia（墨尔本大学数学与统计学学院） 纠错

专题命中 可控生成 ：diffusion(title,abstract)；分类 cs.CV

When and Where do Data Poisons Attack Textual Inversion?

Jeremy Styborski, Mingzhi Lyu, Jiayou Lu, Nupur Kapur, Adams Kong

机构 * College of Computing and Data Science, Nanyang Technological University, Singapore（计算与数据科学学院，南洋理工大学，新加坡） ； Rapid-Rich Object Search (ROSE) Lab, Nanyang Technological University, Singapore（快速丰富对象搜索（ROSE）实验室，南洋理工大学，新加坡） 纠错

专题命中 可控生成 ：diffusion(abstract)

Comments Accepted to ICCV 2025

Neural Field Turing Machine: A Differentiable Spatial Computer

Akash Malhotra, Nacéra Seghouani

专题命中 图像修复 ：inpainting(abstract)

Comments 11 Pages, 6 Figures

LATINO-PRO: LAtent consisTency INverse sOlver with PRompt Optimization

Alessio Spagnoletti, Jean Prost, Andrés Almansa, Nicolas Papadakis, Marcelo Pereyra

专题命中 个性化与一致性 ：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments 27 pages, 24 figures, International Conference on Computer Vision, ICCV 2025

Enhancing Robustness in Post-Processing Watermarking: An Ensemble Attack Network Using CNNs and Transformers

Tzuhsuan Huang, Cheng Yu Yeo, Tsai-Ling Huang, Hong-Han Shuai, Wen-Huang Cheng, Jun-Cheng Chen

机构 * National Yang Ming Chiao Tung University（国家阳明交通大学） ； National Taiwan University（国立台湾大学） 纠错

专题命中 图像生成评测 ：image generation(abstract)；diffusion(abstract)；分类 cs.CV

Comments 10 pages

Deeply Supervised Flow-Based Generative Models

Inkyu Shin, Chenglin Yang, Liang-Chieh Chen

机构 * ByteDance Seed（字节跳动种子） 纠错

专题命中 图像生成评测 ：image generation(abstract)；分类 cs.CV

Comments Accepted to ICCV 2025. Project website at https://deepflow-project.github.io/

Towards Digital Twins for Optimal Radioembolization

Nisanth Kumar Panneerselvam, Guneet Mummaneni, Emilie Roncali

专题命中 效率与蒸馏 ：diffusion(abstract)