图像生成

Numerical Cosmology

Romain Teyssier

专题命中 扩散模型 ：diffusion(abstract)

Comments Lectures given at the Les Houches Summer School "The Dark Universe" July/August 2025. 44 pages and 10 figures (excluding references). Prepared for submission to SciPost Physics Lecture Notes

Cosmic Ray Transport and Gamma-Ray Signatures in the Interstellar Medium

Lucas Barreto-Mota, Elisabete M. de Gouveia Dal Pino, Siyao Xu, Alexandre Lazarian, Rafael Alves-Batista, Gaetano Di Marco, Stela Adduci Faria

专题命中 扩散模型 ：diffusion(abstract)

Comments Proceeding ICRC 2025

Dark Matter-Electron Interactions Alter the Luminosity and Spectral Index of M87

Abdelaziz Hussein, Gonzalo Herrera

专题命中 扩散模型 ：diffusion(abstract)

Comments 6+6 pages, 3+2 figures. Comments are welcome

MTIL: Encoding Full History with Mamba for Temporal Imitation Learning

Yulin Zhou, Yuankai Lin, Fanzhe Peng, Jiahui Chen, Kaiji Huang, Hua Yang, Zhouping Yin

机构 * School of Mechanical Science and Engineering, Huazhong University of Science and Technology（机械科学与工程学院，华中科技大学） 纠错

专题命中 扩散模型 ：diffusion(abstract)

Comments Published in IEEE Robotics and Automation Letters (RA-L), 2025. 8 pages, 5 figures

Journal ref IEEE Robotics and Automation Letters, vol. 10, no. 11, pp. 11761-11767, Nov. 2025

Sharp decay estimates and numerical analysis for weakly coupled systems of two subdiffusion equations

Zhiyuan Li, Yikan Liu, Kazuma Wada

专题命中 扩散模型 ：diffusion(abstract)

Comments 29 pages, 7 figures, 2 tables

Journal ref J. Differential Equations, 453(2), 2026, 113826

Limits of funneling efficiency in non-uniformly strained 2D semiconductors

Moshe G. Harats, Kirill I. Bolotin

专题命中 扩散模型 ：diffusion(abstract)

Comments 7 pages, 4 figures

SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models

Peigui Qi, Kunsheng Tang, Wenbo Zhou, Weiming Zhang, Nenghai Yu, Tianwei Zhang, Qing Guo, Jie Zhang

机构 * University of Science and Technology of China（中国科学技术大学） ； Nanyang Technological University（南洋理工大学） 纠错

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

Comments Accepted by ACM CCS 2025, Code is available at [this https URL](https://github.com/pgqihere/safeguider)

Playmate: Flexible Control of Portrait Animation via 3D-Implicit Space Guided Diffusion

Xingpei Ma, Jiaran Cai, Yuansheng Guan, Shenneng Huang, Qiang Zhang, Shunsi Zhang

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

Journal ref Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41791-41806, 2025

OS-HGAdapter: Open Semantic Hypergraph Adapter for Large Language Models Assisted Entropy-Enhanced Image-Text Alignment

Rongjun Chen, Chengsi Yao, Jinchang Ren, Xianxian Zeng, Peixian Wang, Jun Yuan, Jiawen Li, Huimin Zhao, Xu Lu

机构 * School of Computer Science, Guangdong Polytechnic Normal University（广东 polytechnic 正规大学计算机学院） 纠错

专题命中 可控生成 ：text-to-image(abstract)；分类 cs.CV、cs.MM

MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent

Xinyao Liao, Xianfang Zeng, Liao Wang, Gang Yu, Guosheng Lin, Chi Zhang

机构 * Nanyang Technological University（南洋理工大学） ； StepFun ； Westlake University（西湖大学） 纠错

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

Unconditional CNN denoisers contain sparse semantic representation of images

Zahra Kadkhodaie, Stéphane Mallat, Eero Simoncelli

机构 * New York University（纽约大学） ； Flatiron Institute（Flatiron研究所） ； Collège de France（法兰西学院） 纠错

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

Ultra High-Resolution Image Inpainting with Patch-Based Content Consistency Adapter

Jianhui Zhang, Sheng Cheng, Qirui Sun, Jia Liu, Wang Luyang, Chaoyu Feng, Chen Fang, Lei Lei, Jue Wang, Shuaicheng Liu

机构 * University of Electronic Science and Technology of China（电子科技大学） ； Megvii Technology（华米科技） ； Dzine AI, SeeKoo（Dzine AI，SeeKoo） 纠错

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

Local-Global Context-Aware and Structure-Preserving Image Super-Resolution

Sanchar Palit, Subhasis Chaudhuri, Biplab Banerjee

机构 * Indian Institute of Technology Bombay（印度班加罗尔理工学院） 纠错

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

Comments 10 pages, 11 figures

Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check

Sungjun Cho, Dasol Hwang, Frederic Sala, Sangheum Hwang, Kyunghyun Cho, Sungmin Cha

机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； LG AI Research（LG人工智能研究） ； Seoul National University of Science and Technology（首尔科学技术大学） ； New York University（纽约大学） ； Genentech（基因泰克） 纠错

专题命中 图像生成评测 ：text-to-image(abstract)；diffusion(abstract)

Comments 20 pages, 11 figures

An extended Merton problem with relaxed benchmark tracking

Lijun Bo, Yijie Huang, Xiang Yu

专题命中 图像生成评测 ：diffusion(abstract)

Comments Final version, forthcoming in Mathematical Finance