图像生成

Inpaint4Drag: Repurposing Inpainting Models for Drag-Based Image Editing via Bidirectional Warping

Jingyi Lu, Kai Han

机构 * Visual AI Lab, The University of Hong Kong（视觉人工智能实验室，香港大学） 纠错

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

Comments Accepted to ICCV 2025. Project page: https://visual-ai.github.io/inpaint4drag/

High-resolution efficient image generation from WiFi CSI using a pretrained latent diffusion model

Eshan Ramesh, Takayuki Nishio

机构 * School of Engineering, Institute of Science Tokyo（东京科学研究所工程学院） 纠错

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

Comments 6 pages, 4 figures

HypDAE: Hyperbolic Diffusion Autoencoders for Hierarchical Few-shot Image Generation

Lingxiao Li, Kaixuan Fan, Boqing Gong, Xiangyu Yue

机构 * MMLab, The Chinese University of Hong Kong（香港中文大学） ； Boston University（波士顿大学） 纠错

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

Comments ICCV 2025, Code is available at: https://github.com/lingxiao-li/HypDAE

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

Generating Synthetic Contrast-Enhanced Chest CT Images from Non-Contrast Scans Using Slice-Consistent Brownian Bridge Diffusion Network

Pouya Shiri, Xin Yi, Neel P. Mistry, Samaneh Javadinia, Mohammad Chegini, Seok-Bum Ko, Amirali Baniasadi, Scott J. Adams

机构 * Department of Medical Imaging, University of Saskatchewan（医学成像系，萨斯喀彻温大学） ； Department of Electrical and Computer Engineering, University of Saskatchewan（电气与计算机工程系，萨斯喀彻温大学） 纠错

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

Masked Diffusion Language Models with Frequency-Informed Training

Despoina Kosmopoulou, Efthymios Georgiou, Vaggelis Dorovatas, Georgios Paraskevopoulos, Alexandros Potamianos

机构 * National Technical University of Athens（国家技术大学雅典） ； Archimedes RU, Athena RC（阿基米德RU，雅典RC） ； University of Bern（伯恩大学） ； Institute of Language and Signal Processing, Athena RC（语言与信号处理研究所，雅典RC） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)

Comments Preprint

Plug-and-Play Latent Diffusion for Electromagnetic Inverse Scattering with Application to Brain Imaging

Rui Guo, Yi Zhang, Yhonatan Kvich, Tianyao Huang, Maokun Li, Yonina C. Eldar

专题命中 扩散模型 ：diffusion(title,abstract)

On convergence of upwinding Petrov-Galerkin methods for convection-diffusion

Constantin Bacuta

专题命中 扩散模型 ：diffusion(title,abstract)

Comments 19 pages, one figure created by latex

Train-Once Plan-Anywhere Kinodynamic Motion Planning via Diffusion Trees

Yaniv Hassidof, Tom Jurgenson, Kiril Solovey

机构 * Viterbi Faculty of Electrical and Computer Engineering（电气与计算机工程学院） ； Technion–Israel Institute of Technology（技术学院–以色列理工学院） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)

Comments Accepted to CoRL 2025, Project page: https://sites.google.com/view/ditree. v2: Abstract updated

Diffusion Monte Carlo calculation of compact $T_{cs0}$ and $T_{c\bar{s}0}$ tetraquarks

M. C. Gordillo, J. Segovia

专题命中 扩散模型 ：diffusion(title,abstract)

Comments 1 figure, 2 tables

Deep asymptotic expansion method for solving singularly perturbed time-dependent reaction-advection-diffusion equations

Qiao Zhu, Dmitrii Chaikovskii, Bangti Jin, Ye Zhang

专题命中 扩散模型 ：diffusion(title,abstract)

CDM: Contact Diffusion Model for Multi-Contact Point Localization

Seo Wook Han, Min Jun Kim

机构 * Intelligent Robotic Systems Laboratory, Korea Advanced Institute of Science and Technology（韩国科学技术院智能机器人系统实验室） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)

Comments This paper has been accepted for publication at the 2025 IEEE International Conference on Robotics and Automation (ICRA), Atlanta, USA

In-Context Policy Adaptation via Cross-Domain Skill Diffusion

Minjong Yoo, Woo Kyung Kim, Honguk Woo

专题命中 扩散模型 ：diffusion(title,abstract)

Comments 9 pages

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 2025

Don't Trade Off Safety: Diffusion Regularization for Constrained Offline RL

Junyu Guo, Zhi Zheng, Donghao Ying, Ming Jin, Shangding Gu, Costas Spanos, Javad Lavaei

机构 * University of California Berkeley（加州大学伯克利分校） ； Virginia Tech（弗吉尼亚理工大学） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)

Active thermodynamics of inertial chiral active gases: equation of state and edge currents

Lorenzo Caprini, Umberto Marini Bettolo Marconi, Benno Liebchen, Hartmut Löwen

专题命中 扩散模型 ：diffusion(abstract)

Magnetorotational and convective instabilities in a thin layer of electrically conductive nanofluid under an external helical magnetic field

M. I. Kopp, V. V. Yanovsky

专题命中 扩散模型 ：diffusion(abstract)

Comments Submitted to Functional Materials. 36 pages, 15 figures

Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance

Yang Zhang, Chenwei Wang, Ouyang Lu, Yuan Zhao, Yunfei Ge, Zhenglong Sun, Xiu Li, Chi Zhang, Chenjia Bai, Xuelong Li

机构 * Institute of Artificial Intelligence, China Telecom（中国电信人工智能研究院） ； Tsinghua University（清华大学） ； The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； Northwestern Polytechnical University（西北工业大学） 纠错

专题命中 扩散模型 ：diffusion(abstract)

Comments The first three authors contributed equally

Weak solutions and sharp interface limit of the anisotropic Cahn-Hilliard equation with disparate mobility and inhomogeneous potential

Charles Elbar, Andrea Poiatti

专题命中 扩散模型 ：diffusion(abstract)

Comments 37 pages + Appendix + References

Theory of Transient Heat Conduction

David E. Crawford, Yi Zeng, Judith Vidal, Jianjun Dong

专题命中 扩散模型 ：diffusion(abstract)

Comments 38 pages, 4 figures

Cutting Sequence Diffuser: Sim-to-Real Transferable Planning for Object Shaping by Grinding

Takumi Hachimine, Jun Morimoto, Takamitsu Matsubara

机构 * Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Nara, Japan（信息科学研究生院，科学技术研究院（NAIST），奈良，日本） ； Department of Systems Science, Graduate School of Informatics, Kyoto University（信息系统学部，京都大学） ； Brain Information Communication Research Laboratory Group (BICR), Advanced Telecommunications Research Institute International (ATR), Kyoto, Japan（脑信息通信研究实验室组（BICR），国际电信研究中心（ATR），京都，日本） 纠错

专题命中 扩散模型 ：diffusion(abstract)

Comments 8 pages, Accepted by Robotics and Automation Letter

FEniCSx-pctools: Tools for PETSc block linear algebra preconditioning in FEniCSx

Martin Řehoř, Jack S. Hale

专题命中 扩散模型 ：diffusion(abstract)

Comments 12 pages, 8 figures, 1 table

A model-data asymptotic-preserving neural network method based on micro-macro decomposition for gray radiative transfer equations

Hongyan Li, Song Jiang, Wenjun Sun, Liwei Xu, Guanyu Zhou

机构 * School of Mathematical Sciences, University of Electronic Science（数学科学学院，电子科技大学） ； Institute of Applied Physics（应用物理研究所） ； Institute of Fundamental and Frontier Sciences, University of Electronic Science（基础与前沿科学研究所，电子科技大学） 纠错

专题命中 扩散模型 ：diffusion(abstract)

Mo Atom Rearrangement Drives Layer-Dependent Reactivity in Two-Dimensional MoS2

Zifan Wang, Jiaxuan Wen, Tina Mihm, Shaopeng Feng, Kelvin Huang, Jing Tang, Tianshu Li, Liangbo Liang, Sahar Sharifzadeh, Keji Lai, Xi Ling

专题命中 扩散模型 ：diffusion(abstract)

Comments 41 pages, 20 figures

Spatial Patterning and Selection: How the Environment Shapes Molecular Complexity

Alexandre Champagne-Ruel, Christopher P. Kempes, Cole Mathis

专题命中 扩散模型 ：diffusion(abstract)

Comments 14 pages, 7 figures

BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling

Hao Li, Yu-Hao Huang, Chang Xu, Viktor Schlegel, Renhe Jiang, Riza Batista-Navarro, Goran Nenadic, Jiang Bian

机构 * Microsoft Research（微软研究院） ； The University of Manchester, UK（英国曼彻斯特大学） ； Nanjing University, China（南京大学） ； Imperial College London, Imperial Global Singapore, Singapore（伦敦帝国学院，新加坡帝国全球分校，新加坡） ； The University of Tokyo, Japan（日本东京大学） 纠错

专题命中 可控生成 ：diffusion(title)

Comments ICML 2025 Main Conference

Disentangled Clothed Avatar Generation with Layered Representation

Weitian Zhang, Yichao Yan, Sijing Wu, Manwen Liao, Xiaokang Yang

机构 * MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University（人工智能教育部重点实验室、人工智能研究院、上海交通大学） ； The University of Hong Kong（香港大学） 纠错

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

Comments ICCV 2025 highlight, project page: https://olivia23333.github.io/LayerAvatar/

Improving Spatial Resolution of Background Oriented Schlieren Based on Directional Rays

Xiang Li, Muen Gao, Weiran Wang, Jiawei Li, Chong Pan, Jinjun Wang, Yuan Xiong

专题命中 可控生成 ：image generation(abstract)

MAIA: An Inpainting-Based Approach for Music Adversarial Attacks

Yuxuan Liu, Peihong Zhang, Rui Sang, Zhixin Li, Shengchen Li

专题命中 图像修复 ：inpainting(title,abstract)

Comments Accepted at ISMIR2025

Synthetic Acceleration Preconditioners for Parametric Radiative Transfer Equations based on Trajectory-Aware Reduced Order Models

Ning Tang, Zhichao Peng

专题命中 效率与蒸馏 ：diffusion(abstract)

Comments 32 pages, 9 figures

FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies

Moritz Reuss, Hongyi Zhou, Marcel Rühle, Ömer Erdinç Yağmurlu, Fabian Otto, Rudolf Lioutikov

机构 * Intuitive Robots Lab（直观机器人实验室） ； Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院） ； Microsoft Research（微软研究院） 纠错

专题命中 效率与蒸馏 ：diffusion(abstract)

Comments Published at CoRL 2025