图像生成

Prediction of sulphate hazes in the lower Venus atmosphere

Peter Woitke, Manuel Scherf, Christiane Helling, Paul B. Rimmer, Martin Ferus, Helmut Lammer, Fabian Weichbold, Kateřina Němečková, Petr Eminger, Jaroslav Kačina, Tereza Constantinou

专题命中 扩散模型 ：diffusion(abstract)

Comments 18 pages, accepted by PSJ on 27-Aug-2025

On the orbital variability of gamma-ray emission in $γ^2$ Velorum

Agnibha De Sarkar

专题命中 扩散模型 ：diffusion(abstract)

Comments 9 pages, 3 figures, 2 tables; accepted for publication in Astronomy & Astrophysics (A&A)

Journal ref A&A 701, A18 (2025)

LGDE: Local Graph-based Dictionary Expansion

Juni Schindler, Sneha Jha, Xixuan Zhang, Kilian Buehling, Annett Heft, Mauricio Barahona

机构 * Department of Surgery & Cancer, Imperial College London, United Kingdom（伦敦帝国学院外科与癌症系） ； Weizenbaum Institute Berlin, Germany（柏林Weizenbaum研究所） ； Institute for Media and Communication Studies, Free University of Berlin, Germany（柏林自由大学媒体与传播研究所） ； Institute for Research on Far Right Extremism, University of Tübingen, Germany（图宾根大学右翼极端主义研究所） 纠错

专题命中 扩散模型 ：diffusion(abstract)

Comments Python code available at: https://github.com/barahona-research-group/LGDE

Boundedness estimates for nonlinear nonlocal kinetic Kolmogorov-Fokker-Planck equations

Francesca Anceschi, Mirco Piccinini

专题命中 扩散模型 ：diffusion(abstract)

Journal ref Nonlinear Differ. Equ. Appl. 32, 121 (2025)

Artificial neural network solver for Fokker-Planck and Koopman eigenfunctions

Max Kreider, Peter J. Thomas, Yao Li

专题命中 扩散模型 ：diffusion(abstract)

Generative AI Against Poaching: Latent Composite Flow Matching for Wildlife Conservation

Lingkai Kong, Haichuan Wang, Charles A. Emogor, Vincent Börsch-Supan, Lily Xu, Milind Tambe

专题命中 扩散模型 ：diffusion(abstract)

Comments Fix the feature color for the detection head in Figure 2

General Linear-Quadratic Mean Field Stochastic Differential Game with Common Noise: A Direct Method

Yu Si, Jingtao Shi

专题命中 扩散模型 ：diffusion(abstract)

Comments 32 pages, 4 figures

An Extension of the Localized Artificial Diffusivity Method for Immiscible and High Density Ratio Flows

Steven R. Brill, Britton J. Olson, Guillaume T. Bokman

专题命中 扩散模型 ：diffusion(abstract)

NEP-MB-pol: A unified machine-learned framework for fast and accurate prediction of water's thermodynamic and transport properties

Ke Xu, Ting Liang, Nan Xu, Penghua Ying, Shunda Chen, Ning Wei, Jianbin Xu, Zheyong Fan

专题命中 扩散模型 ：diffusion(abstract)

Comments 12 pages, 4 figures in the main text; 8 figures in the SI

Journal ref npj Computational Materials, 11, 279 (2025)

Interact-Custom: Customized Human Object Interaction Image Generation

Zhu Xu, Zhaowen Wang, Yuxin Peng, Yang Liu

机构 * Wangxuan Institute of Computer Technology, Peking University（北京大学计算机技术研究院） ； Adobe Research（Adobe研究） 纠错

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

MIDAS: Multimodal Interactive Digital-humAn Synthesis via Real-time Autoregressive Video Generation

Ming Chen, Liyuan Cui, Wenyuan Zhang, Haoxian Zhang, Yan Zhou, Xiaohan Li, Songlin Tang, Jiwen Liu, Borui Liao, Hejia Chen, Xiaoqiang Liu, Pengfei Wan

机构 * Kling Team, Kuaishou Technology（快手科技 Kling 团队） ； Zhejiang University（浙江大学） ； Tsinghua University（清华大学） 纠错

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

Comments Technical Report. Project Page: https://chenmingthu.github.io/milm/

Pixel Motion as Universal Representation for Robot Control

Kanchana Ranasinghe, Xiang Li, E-Ro Nguyen, Cristina Mata, Jongwoo Park, Michael S Ryoo

机构 * Stony Brook University（石溪大学） 纠错

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

T-Stars-Poster: A Framework for Product-Centric Advertising Image Design

Hongyu Chen, Min Zhou, Jing Jiang, Jiale Chen, Yang Lu, Zihang Lin, Bo Xiao, Tiezheng Ge, Bo Zheng

机构 * Alibaba Group（阿里巴巴集团） ； Beijing University of Posts and Telecommunications（北京邮电大学） 纠错

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

Comments Accepted by CIKM 2025

Robust ID-Specific Face Restoration via Alignment Learning

Yushun Fang, Lu Liu, Xiang Gao, Qiang Hu, Ning Cao, Jianghe Cui, Gang Chen, Xiaoyun Zhang

机构 * Shanghai Jiao Tong University, Shanghai, 200240, China（上海交通大学） ； E-surfing Vision Technology Co., Ltd., China（E-surfing视觉技术有限公司） 纠错

专题命中 图像修复 ：diffusion(abstract)；分类 cs.CV

Comments PRCV2025 Accepted

ZIM: Zero-Shot Image Matting for Anything

Beomyoung Kim, Chanyong Shin, Joonhyun Jeong, Hyungsik Jung, Se-Yun Lee, Sewhan Chun, Dong-Hyun Hwang, Joonsang Yu

机构 * NAVER Cloud, ImageVision（NAVER云，ImageVision） 纠错

专题命中 图像修复 ：inpainting(abstract)；分类 cs.CV

Comments ICCV 2025 (Highlight)

Persode: Personalized Visual Journaling with Episodic Memory-Aware AI Agent

Seokho Jin, Manseo Kim, Sungho Byun, Hansol Kim, Jungmin Lee, Sujeong Baek, Semi Kim, Sanghum Park, Sung Park

专题命中 个性化与一致性 ：text-to-image(abstract)

OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning

Yuan Gong, Xionghui Wang, Jie Wu, Shiyin Wang, Yitong Wang, Xinglong Wu

机构 * ByteDance Inc.（字节跳动公司） 纠错

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

Comments project url: https://one-reward.github.io

DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness

Ruining Li, Chuanxia Zheng, Christian Rupprecht, Andrea Vedaldi

机构 * Visual Geometry Group, University of Oxford（牛津大学视觉几何组） 纠错

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

Comments Accepted at ICCV 2025 (Highlight). Project page: https://ruiningli.com/dso

VarDiU: A Variational Diffusive Upper Bound for One-Step Diffusion Distillation

Leyang Wang, Mingtian Zhang, Zijing Ou, David Barber

机构 * University College London（伦敦大学学院） ； Imperial College London（伦敦帝国学院） 纠错

专题命中 效率与蒸馏 ：diffusion(title,abstract)

Comments Leyang Wang and Mingtian Zhang contributed equally to this work

Unleashing Uncertainty: Efficient Machine Unlearning for Generative AI

Christoforos N. Spartalis, Theodoros Semertzidis, Petros Daras, Efstratios Gavves

机构 * ITI, Centre for Research \& Technology Hellas, Greece ； University of Amsterdam, Netherlands 纠错

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

Comments ICML 2025 workshop on Machine Unlearning for Generative AI