arXivDaily arXiv每日学术速递 周一至周五更新

视觉与机器人

图像生成

图像生成、文生图、图像编辑、扩散模型和可控生成。

2026-06-24 至 2026-06-24 共收录 18 信号源:cs.CV, cs.GR, cs.MM

1. 扩散模型 14 篇

2512.15067 2026-06-24 cs.LG cs.AI cs.SY eess.SY 版本更新 82%

EMFusion: Uncertainty-Aware Conditional Diffusion Model for Multivariate Narrow-band Exposure Forecasting

EMFusion: 一种考虑不确定性的条件扩散框架用于无线网络中频率选择性电磁场预测

Zijiang Yan, Yixiang Huang, Jianhua Pei, Hina Tabassum, Luca Chiaraviglio

机构 * department of Electrical Engineering and Computer Science, York University(电气工程与计算机科学系,约克大学) School of Electrical and Electronic Engineering, Huazhong University of Science and Technology(电子与电气工程学院,华中科技大学) Central China Branch of State Grid Corporation of China(国家电网公司中部分部) Department of Electronic Engineering, University of Rome Tor Vergata(罗马大学Tor Vergata电子工程系) Consorzio Nazionale Interuniversitario per le Telecomunicazioni (CNIT)(国家大学间电信研究会(CNIT))

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

AI总结 本文提出EMFusion框架,通过整合时间、季节等上下文因素,提供不确定性估计,以提升无线网络中频率选择性电磁场预测的准确性。

Comments Accepted in IEEE Transactions on Network Science and Engineering

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.09508 2026-06-24 eess.AS 版本更新 82%

A Fast Solver for Interpolating Stochastic Differential Equation Diffusion Models for Speech Restoration

用于语音恢复的插值随机微分方程扩散模型的快速求解器

Bunlong Lay, Timo Gerkmann

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

AI总结 针对SGMSE+等插值扩散模型,提出一种快速求解器,仅需10次神经网络评估即可完成语音恢复任务。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.22249 2026-06-24 cs.CV 版本更新 79%

D3Seg: Dependency-Aware Diffusion for Brain Tumor Segmentation with Missing Modalities

D3Seg: 依赖感知的扩散模型用于缺失模态的脑肿瘤分割

Danish Ali, Ajmal Mian, Naveed Akhtar, Ghulam Mubashar Hassan

机构 * The University of Western Australia(西澳大学) The University of Melbourne(墨尔本大学)

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

AI总结 本文提出D3Seg模型,通过多跳模态图融合、轻量扩散插补机制和概率空间决策细化,解决缺失MRI模态下的脑肿瘤分割问题,提升分割性能并保持计算效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.29578 2026-06-24 cs.CV 版本更新 79%

Emotion Diffusion Classifier with Adaptive Margin Discrepancy Training for Facial Expression Recognition

具有自适应间隔差异训练的情感扩散分类器用于面部表情识别

Rongkang Dong, Cuixin Yang, Cong Zhang, Yushen Zuo, Kin-Man Lam

机构 * Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University(香港理工大学电子与电气工程系) School of Control Science and Engineering, Shandong University(山东大学控制科学与工程学院)

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

AI总结 提出基于条件生成扩散模型的情感扩散分类器(EmoDC),通过自适应间隔差异训练(AMDiT)动态调整间隔,提升噪声预测判别能力,在面部表情识别中优于现有判别模型。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.13659 2026-06-24 physics.chem-ph cond-mat.soft 版本更新 78%

Ion-Specific Anomalous Water Diffusion in Aqueous Electrolytes: A Machine-Learned Many-Body Force Field Study with MACE

具有离子特异性的水异常扩散在水合电解质中的研究:基于MACE的机器学习多体力场研究

Massimo Ciacchi, Ilnur Saitov, Nico Di Fonte, Isabella Daidone, Carlo Pierleoni

专题命中 扩散模型 :diffusion(title,abstract)

AI总结 研究通过机器学习多体力场模拟揭示了水在电解质溶液中的离子特异性异常扩散现象,改进了NaCl溶液的模拟结果,揭示了离子水合壳层对水扩散的影响机制。

Comments 26 pages, 24 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.21450 2026-06-24 cs.CE q-bio.BM 版本更新 78%

CMADiff: Cross-Modal Aligned Diffusion for Controllable Protein Generation

CMADiff: 用于可控蛋白质生成的跨模态对齐扩散

Changjian Zhou, Yuexi Qiu, Jiafeng Li, Jia Song, Wensheng Xiang

专题命中 扩散模型 :diffusion(title,abstract)

AI总结 提出CMADiff框架,通过条件变分自编码器整合理化特征,并利用对比学习模块BioAligner对齐文本描述与蛋白质特征,实现基于文本驱动的可控蛋白质序列生成。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.17873 2026-06-24 cond-mat.mtrl-sci cond-mat.dis-nn cond-mat.soft cond-mat.stat-mech 版本更新 78%

Precise Determination of the Long-Time Asymptotics of the Diffusion Spreadability of Two-Phase Media

两相介质扩散可扩展性长时间渐近行为的精确确定

Shaobing Yuan, Salvatore Torquato

专题命中 扩散模型 :diffusion(title,abstract)

AI总结 通过引入高阶修正项和解析性质,提出改进算法精确提取两相介质扩散可扩展性的长时标度指数α,并构造两点Padé近似逼近全时域行为。

Comments 17 pages, 9 figures; v2: accepted by PRE

Journal ref Phys. Rev. E, 113 (2026) 065421

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.18645 2026-06-24 math.AP 版本更新 78%

Global Existence and Diffusive Limits for a Class of Nonlocal Reaction-Diffusion Systems

一类非局部反应扩散系统的全局存在性与扩散极限

Md Shah Alam, Jeff Morgan

专题命中 扩散模型 :diffusion(title,abstract)

AI总结 研究一类具有非局部扩散的半线性反应扩散系统,在拟正性和广义质量控制条件下证明全局存在唯一性,并通过线性中间和条件建立L^p一致有界性,推广了Laurencot和Walker的扩散极限结果。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.04767 2026-06-24 cs.LG 版本更新 78%

ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs

ParallelBench: 理解扩散大语言模型中并行解码的权衡

Wonjun Kang, Kevin Galim, Seunghyuk Oh, Minjae Lee, Yuchen Zeng, Shuibai Zhang, Coleman Hooper, Yuezhou Hu, Hyung Il Koo, Nam Ik Cho, Kangwook Lee

机构 * FuriosaAI UW-Madison(威斯康星大学麦迪逊分校) Microsoft Research(微软研究院) UC Berkeley(加州大学伯克利分校) Seoul National University(首尔国立大学) KRAFTON Ludo Robotics Project(Ludo机器人项目)

专题命中 扩散模型 :diffusion(title,abstract)

AI总结 针对扩散LLM并行解码导致生成质量下降的问题,通过信息论分析和合成实验揭示其根本限制,并提出首个专门基准ParallelBench,系统评估发现并行解码在现实任务中质量损失严重,且现有策略无法根据任务难度调整并行度。

Comments Accepted at ICLR 2026. Project Page: https://parallelbench.github.io

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.05896 2026-06-24 cs.CV 版本更新 57%

Resonant Minds: Closed-Loop Social Avatars with Theory of Mind

共鸣心智:具备心智理论的闭环社交虚拟人

Jianxu Shangguan, Jing Xu, Hang Ye, Xiaoxuan Ma, Yizhou Wang, Jenq-Neng Hwang, Wentao Zhu

机构 * University of Washington(华盛顿大学) Peking University(北京大学) Carnegie Mellon University(卡内基梅隆大学) Eastern Institute of Technology, Ningbo(宁波工程技术学院)

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

AI总结 提出一个闭环双智能体框架,通过整合感知、社会推理(基于心智理论)和多模态生成,实现具备社交智能的虚拟人,并在信息不对称数据集上取得优于全信息脚本模式的对话质量。

Comments Project page: https://resonantminds.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.17917 2026-06-24 cond-mat.soft physics.flu-dyn 版本更新 50%

Lateral hydrodynamics in supported membranes: The Evans-Sackmann model and its extensions

支撑膜中的横向水动力学:Evans-Sackmann模型及其扩展

Yuto Hosaka, David Andelman, Shigeyuki Komura

专题命中 扩散模型 :diffusion(abstract)

AI总结 本文综述了Evans-Sackmann水动力学模型在支撑流体膜中横向传输的理论发展和现代应用,讨论了模型的原始形式、扩展以及其在膜相分离动力学和相关扩散中的统一作用。

Comments 13 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.16603 2026-06-24 hep-ph astro-ph.CO 版本更新 50%

Baryon Asymmetry from Electroweak-Symmetric Domain Walls

重子不对称性来自电弱对称域墙

Jacopo Azzola, Oleksii Matsedonskyi, Andreas Weiler

专题命中 扩散模型 :diffusion(abstract)

AI总结 研究电弱对称域墙在电弱破缺等离子体中通过产生手性不对称性来生成重子不对称性,分析壁厚、CP破坏源和扩散长度的层次关系及参数极限下的标度行为。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.15370 2026-06-24 cs.SI 版本更新 50%

The Significance of User Characteristics for Reposting Prediction on X: A Comparative Analysis Under Distribution Shift

用户特征对X平台转发预测的重要性:分布漂移下的比较分析

Ziming Xu, Shi Zhou, Vasileios Lampos, Ingemar J. Cox

专题命中 扩散模型 :diffusion(abstract)

AI总结 针对分布漂移下X平台转发预测任务,比较帖子特征与用户特征的效果,发现用户特征(如社交关系、历史行为)在未见话题上F1超过0.70,而帖子特征仅约0.12,表明转发决策主要由稳定用户特征驱动。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.21916 2026-06-24 cs.RO 版本更新 50%

Prior Reinforce: Goal-Conditioned Dynamic Manipulation with Limited Trials

Prior Reinforce: 有限试验下的目标条件动态操控

Yihang Hu, Pingyue Sheng, Yuyang Liu, Shengjie Wang, Yang Gao

机构 * IIIS, Tsinghua University(清华大学智能学院) Shanghai Qi Zhi Institute(上海启智研究院) Spirit AI

专题命中 扩散模型 :diffusion(abstract)

AI总结 提出Prior Reinforce框架,利用条件扩散模型从少量演示学习运动流形,并在低维条件空间通过反馈驱动优化适应新目标,实现少至十次试验内的动态操控。

Comments Accepted to the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏

2. 图像修复 1 篇

2106.06998 2026-06-24 cs.LG cs.NA math.NA 版本更新 50%

XConv: Low-memory stochastic backpropagation for convolutional layers

XConv: 卷积层的低内存随机反向传播

Anirudh Thatipelli, Jeffrey Sam, Mathias Louboutin, Ali Siahkoohi, Rongrong Wang, Felix J. Herrmann

机构 * University of Central Florida(中央佛罗里达大学) Rice University(里士满大学) DevitoCodes Ltd(DevitoCodes有限公司) Michigan State University(密歇根州立大学) Georgia Institute of Technology(佐治亚理工学院)

专题命中 图像修复 :inpainting(abstract)

AI总结 提出XConv方法,通过存储激活的压缩投影并利用多通道随机迹估计近似梯度,在不增加计算、不约束架构、不大量修改代码的情况下,大幅降低卷积层反向传播的内存需求。

详情

展开后加载摘要…

URL PDF HTML 收藏

3. 个性化与一致性 1 篇

2602.09303 2026-06-24 cs.LG cs.NA math.NA 版本更新 67%

Stabilizing Physics-Informed Consistency Models via Structure-Preserving Training

通过保结构训练稳定物理信息一致性模型

Che-Chia Chang, Chen-Yang Dai, Te-Sheng Lin, Ming-Chih Lai, Chieh-Hsin Lai

机构 * Institute of Artificial Intelligence Innovation(人工智能创新研究所) National Yang Ming Chiao Tung University(国立阳明交通大学) Department of Applied Mathematics(应用数学系) National Center for Theoretical Sciences(理论科学研究中心) National Taiwan University(国立台湾大学)

专题命中 个性化与一致性 :diffusion(abstract);inpainting(abstract)

AI总结 提出物理信息一致性建模框架,通过保结构两阶段训练策略和两步残差目标,解决物理约束下一致性训练的不稳定性,实现快速、高保真的PDE求解。

Comments Accepted to KDD 2026

Journal ref Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 (KDD '26), August 09--13, 2026, Jeju Island, Republic of Korea

详情

展开后加载摘要…

URL PDF HTML 收藏

4. 图像生成评测 1 篇

2606.02800 2026-06-24 cs.CV cs.AI cs.LG cs.MM cs.RO 版本更新 62%

Cosmos 3: Omnimodal World Models for Physical AI

Cosmos 3:面向物理AI的全模态世界模型

NVIDIA, :, Aditi, Niket Agarwal, Arslan Ali, Jon Allen, Martin Antolini, Adeline Aubame, Alisson Azzolini, Junjie Bai, Maciej Bala, Yogesh Balaji, Josh Bapst, Aarti Basant, Mukesh Beladiya, Mohammad Qazim Bhat, Zaid Pervaiz Bhat, Dan Blick, Vanni Brighella, Han Cai, Tiffany Cai, Eric Cameracci, Jiaxin Cao, Yulong Cao, Mark Carlson, Carlos Casanova, Ting-Yun Chang, Yan Chang, Yu-Wei Chao, Prithvijit Chattopadhyay, Roshan Chaudhari, Chieh-Yun Chen, Junyu Chen, Ke Chen, Qizhi Chen, Wenkai Chen, Xiaotong Chen, Yu Chen, An-Chieh Cheng, Click Cheng, Xiu Chia, Jeana Choi, Chaeyeon Chung, Wenyan Cong, Yin Cui, Magdalena Dadela, Nalin Dadhich, Wenliang Dai, Joyjit Daw, Alperen Degirmenci, Rodrigo Vieira Del Monte, Robert Denomme, Sameer Dharur, Marco Di Lucca, Ke Ding, Wenhao Ding, Yifan Ding, Yuzhu Dong, Nicole Drumheller, Yilun Du, Aigul Dzhumamuratova, Aleksandr Efitorov, Hamid Eghbalzadeh, Naomi Eigbe, Imad El Hanafi, Hassan Eslami, Benedikt Falk, Jiaojiao Fan, Jim Fan, Amol Fasale, Sergiy Fefilatyev, Liang Feng, Francesco Ferroni, Sanja Fidler, Xiao Fu, Vikram Fugro, Prashant Gaikwad, TJ Galda, Katelyn Gao, Yihuai Gao, Wenhang Ge, Sreyan Ghosh, Arushi Goel, Vivek Goel, Akash Gokul, Rama Govindaraju, Jinwei Gu, Miguel Guerrero, Elfie Guo, Aryaman Gupta, Siddharth Gururani, Hugo Hadfield, Song Han, Ankur Handa, Zekun Hao, Mohammad Harrim, Ali Hassani, Nathan Hayes-Roth, Yufan He, Chris Helvig, Cyrus Hogg, Madison Huang, Michael Huang, Sophia Huang, Yufan Huang, Jacob Huffman, DeLesley Hutchins, Suneel Indupuru, Boris Ivanovic, Arihant Jain, Joel Jang, Ryan Ji, Yanan Jian, Dongfu Jiang, Jingyi Jin, Atharva Joshi, Nikhilesh Joshi, Pranjali Joshi, Andy Ju, Jaehun Jung, Weiwei Kang, Scott Kassekert, Jan Kautz, Ashna Khetan, Julia Kiczka, Slawek Kierat, Gwanghyun Kim, Kuno Kim, Sunny Kim, Kezhi Kong, Xin Kong, Zhifeng Kong, Tomasz Kornuta, Egor Krivov, Hui Kuang, Saurav Kumar, Chia-Wen Kuo, George Kurian, Wojciech Kutak, JF Lafleche, Himangshu Lahkar, Omar Laymoun, Jayjun Lee, Sanggil Lee, Gabriele Leone, Boyi Li, Freya Li, Jiajun Li, Jinfeng Li, Ling Li, Pengcheng Li, Shangru Li, Tingle Li, Xiaolong Li, Xuan Li, Zhaoshuo Li, Zhiqi Li, Hao Liang, Maosheng Liao, Chen-Hsuan Lin, Tsung-Yi Lin, Ming-Yu Liu, Sifei Liu, Zihan Liu, Hai Loc Lu, Xiangyu Lu, Alice Luo, Ruipu Luo, Wenjie Luo, Jiangran Lyu, Martin Ding Ma, Nic Ma, Qianli Ma, Dawid Majchrowski, Louis Marcoux, Miguel Martin, Qing Miao, Ashkan Mirzaei, Shreyas Misra, Kaichun Mo, Durra Mohsin, Hyejin Moon, Pawel Morkisz, Saeid Motiian, Kirill Motkov, Seungjun Nah, Yashraj Narang, Deepak Narayanan, Thabang Ngazimbi, Julian Ouyang, Shubham Pachori, David Page, Yatian Pang, Sehwi Park, Mahesh Patekar, Mostofa Patwary, Marco Pavone, Trung Pham, Wei Ping, Soha Pouya, Shrimai Prabhumoye, Varun Praveen, Delin Qu, Hesam Rabeti, Morteza Ramezanali, Marilyn Reeb, Xuanchi Ren, Kristen Rumley, Wojciech Rymer, Jun Saito, Yeongho Seol, John Shao, Piyush Shekdar, Tianwei Shen, Humphrey Shi, Min Shi, Stella Shi, Kevin Shih, Mohammad Shoeybi, Mateusz Sieniawski, Shuran Song, Alexander Sotelo, Amir Sotoodeh, Sunil Srinivasa, Vignesh Srinivasakumar, Bartosz Stefaniak, Rahul Heinrich Steiger, Shangkun Sun, Jiaxiang Tang, Shitao Tang, Yangyang Tang, Yue Tang, Tolou Tavakkoli, Kayley Ting, Krzysztof Tomala, Wei-Cheng Tseng, Jibin Varghese, Sergei Vasilev, Thomas Volk, Raju Wagwani, Roger Waleffe, Andrew Z. Wang, Boxiang Wang, Haoxiang Wang, Qiao Wang, Shihao Wang, Shijie Wang, Ting-Chun Wang, Yan Wang, Yu Wang, Rohit Watve, David Wehr, Fangyin Wei, Xinshuo Weng, Jay Zhangjie Wu, Kedi Wu, Hongchi Xia, Summer Xiao, Tianjun Xiao, Kevin Xie, Daguang Xu, Jiashu Xu, Mengyao Xu, Ruqing Xu, Xingqian Xu, Yao Xu, Dinghao Yang, Dong Yang, Hans Yang, Xiaodong Yang, Xuning Yang, Yichu Yang, Yurong You, Zhiding Yu, Hao Yuan, Simon Yuen, Xiaohui Zeng, Pengcuo Zeren, Cindy Zha, Haotian Zhang, Jenny Zhang, Jing Zhang, Liangkai Zhang, Paris Zhang, Shun Zhang, Xuanmeng Zhang, Zhizheng Zhang, Ann Zhao, Yilin Zhao, Yuliya Zhautouskaya, Charles Zhou, Fengzhe Zhou, Shilin Zhu, Yuke Zhu, Dima Zhylko, Artur Zolkowski

机构 * NVIDIA

专题命中 图像生成评测 :text-to-image(abstract);分类 cs.CV、cs.MM

AI总结 提出基于统一混合Transformer架构的全模态世界模型Cosmos 3,联合处理语言、图像、视频、音频和动作序列,在理解和生成任务上达到新最优,为具身智能体提供可扩展的通用骨干。

详情

展开后加载摘要…

URL PDF HTML 收藏

5. 效率与蒸馏 1 篇

2512.11121 2026-06-24 cs.CV eess.IV 版本更新 57%

Generative Manifold Distillation: Aligning Restoration Trajectories with Natural Image Prior

生成式流形蒸馏:将恢复轨迹与自然图像先验对齐

Yuyang Hu, Mojtaba Sahraee-Ardakan, Arpit Bansal, Kangfu Mei, Chenyang Qi, Peyman Milanfar, Mauricio Delbracio

机构 * Google(谷歌) Washington University in St. Louis(圣路易斯华盛顿大学)

专题命中 效率与蒸馏 :text-to-image(abstract);分类 cs.CV

AI总结 提出生成式流形蒸馏(GMD),通过几何流形对齐实现无配对域自适应,利用冻结文本到图像基础模型的流匹配动力学将离流形恢复投影到自然图像流形,并引入质量门控滤波器和源锚定轨迹正则化,无需架构修改或推理延迟即可提升感知质量。

详情

展开后加载摘要…

URL PDF HTML 收藏