图像生成

2504.01308 2025-08-05 cs.CV 57%

Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks

Jiawei Wang, Yushen Zuo, Yuanjun Chai, Zhendong Liu, Yicheng Fu, Yichun Feng, Kin-Man Lam

机构 * University of Science and Technology of China（中国科学技术大学）； The Hong Kong Polytechnic University（香港理工大学）； University of Washington（华盛顿大学）； Nanjing University（南京大学）； Stanford University（斯坦福大学）； University of Chinese Academy of Sciences（中国科学院大学）

专题命中扩散模型：diffusion(abstract)；分类 cs.CV

Comments ICCV 2025

2501.05442 2025-08-05 cs.CV cs.AI eess.IV 57%

Progressive Growing of Video Tokenizers for Temporally Compact Latent Spaces

Aniruddha Mahapatra, Long Mai, David Bourgin, Yitian Zhang, Feng Liu

机构 * Adobe Research（Adobe研究院）； Northeastern University（东北大学）

专题命中扩散模型：diffusion(abstract)；分类 cs.CV

Comments Project website: https://progressive-video-tokenizer.github.io/Pro-MAG/

2411.13120 2025-08-05 cs.CV cs.LG physics.med-ph physics.optics 57%

Virtual Staining of Label-Free Tissue in Imaging Mass Spectrometry

Yijie Zhang, Luzhe Huang, Nir Pillar, Yuzhu Li, Lukasz G. Migas, Raf Van de Plas, Jeffrey M. Spraggins, Aydogan Ozcan

专题命中扩散模型：diffusion(abstract)；分类 cs.CV

Comments 33 Pages, 6 Figures

Journal ref Science Advances (2025)

2508.02224 2025-08-05 math.AP math.PR 50%

Abstract Formulation of Mean-Field Models and Propagation of Chaos

Tau Shean Lim, Chao Dun Teoh

专题命中扩散模型：diffusion(abstract)

Comments 96 pages

2508.02050 2025-08-05 cs.IR 50%

Why Generate When You Can Transform? Unleashing Generative Attention for Dynamic Recommendation

Yuli Liu, Wenjun Kong, Cheng Luo, Weizhi Ma

专题命中扩散模型：diffusion(abstract)

Comments Accepted at ACMMM 2025

2508.02025 2025-08-05 physics.bio-ph physics.app-ph physics.optics 50%

Frequency-Domain Denoising-Based in Vivo Fluorescence Imaging

XuHao Yu, RongYuan Zhang, Zhen Tian, Yixuan Chen, JiaChen Zhang, Yue Yuan, Zheng Zhao, Ben Zhong Tang, Dazhi Hou

专题命中扩散模型：diffusion(abstract)

2508.01890 2025-08-05 physics.flu-dyn 50%

On the Non-Markovian Navier-Stokes Framework for Turbulence Modeling -- A Preliminary Analysis

Siamak Kazemzadeh Hannani, Ehsan Ghaderi

专题命中扩散模型：diffusion(abstract)

2508.01796 2025-08-05 cs.SD eess.AS 50%

Enhancing Spectrogram Realism in Singing Voice Synthesis via Explicit Bandwidth Extension Prior to Vocoder

Runxuan Yang, Kai Li, Guo Chen, Xiaolin Hu

机构 * Institute for Clarity in Documentation（清晰文档研究所）； Inria Paris-Rocquencourt（巴黎-罗克Quantin研究所）； Rajiv Gandhi University（拉朱·甘地大学）； Tsinghua University（清华大学）； Palmer Research Laboratories（帕尔默研究实验室）

专题命中扩散模型：diffusion(abstract)

Comments 7 pages, 8 figures

2508.01755 2025-08-05 math.DS 50%

Dynamic Coupling of Infiltration-Soil Moisture Feedback:Emergent Vegetation Patterns in a Water-Vegetation Model

Juan Yan, Xiaoli Wang, Guohong Zhang, Yuan Yuan

专题命中扩散模型：diffusion(abstract)

2508.01600 2025-08-05 cs.RO 50%

CLASS: Contrastive Learning via Action Sequence Supervision for Robot Manipulation

Sung-Wook Lee, Xuhui Kang, Brandon Yang, Yen-Ling Kuo

机构 * University of Virginia（弗吉尼亚大学）

专题命中扩散模型：diffusion(abstract)

Comments To appear in Proceedings of the Conference on Robot Learning (CoRL) 2025

2508.01567 2025-08-05 physics.optics physics.app-ph 50%

Sub 10 nm Nanochannels Enable Directional Quasi Ballistic Exciton Transport over 5 μm at Room Temperature

Xiao-Jie Wang, Jia-Wei Tan, Xiao-Ze Li, Hong-Hua Fang, Guan-Yao Huang, Yang-Yi Chen, Yuan Luo, Jia-Tai Huang, Gong Wang, Qi-Hua Xiong, Xavier Marie, Hong-Bo Sun

专题命中扩散模型：diffusion(abstract)

2508.01441 2025-08-05 eess.IV 50%

Viscosity Stabilized Plug-and-Play Reconstruction

Arghya Sinha, Trishit Mukherjee, Kunal N. Chaudhury

专题命中扩散模型：diffusion(abstract)

Comments 12 pages, 12 figures

2508.01194 2025-08-05 astro-ph.HE astro-ph.CO 50%

Energy-dependent anisotropy of cosmic-ray muons: A twelve-year study with IceCube Neutrino Observatory

Nabin Upadhya Dhakal, Nabin Bhusal, Manjeet Kunwar, Manil Khatiwada, Shiv Narayan Yadav

专题命中扩散模型：diffusion(abstract)

2508.01025 2025-08-05 physics.optics 50%

Time-resolved infrared photothermal imaging: From transient observations towards the steady-state

Dennis van de Lockand, Daan Wolters, Matz Liebel

专题命中扩散模型：diffusion(abstract)

2508.00940 2025-08-05 cond-mat.stat-mech 50%

Stochastic Calculus Approach to Thermodynamics of Jump Processes

Lars Torbjørn Stutzer

专题命中扩散模型：diffusion(abstract)

Comments Master Thesis

2507.21042 2025-08-05 cond-mat.other 50%

Approximate solutions to the shrinking core model and their interpretation

Cristian Moreno-Pulido, Rachael Olwande, Tim Myers, Francesc Font

专题命中扩散模型：diffusion(abstract)

2506.21562 2025-08-05 cs.CL cs.AI cs.AR 50%

FloorPlan-DeepSeek (FPDS): A multimodal approach to floorplan generation using vector-based next room prediction

Jun Yin, Pengyu Zeng, Jing Zhong, Peilin Li, Miao Zhang, Ran Luo, Shuai Lu

专题命中扩散模型：diffusion(abstract)

2506.08937 2025-08-05 math.NA cs.NA math.PR 50%

Asymptotic error distribution for stochastic Runge--Kutta methods of strong order one

Diancong Jin

专题命中扩散模型：diffusion(abstract)

2503.09078 2025-08-05 cs.RO 50%

Sequential Multi-Object Grasping with One Dexterous Hand

Sicheng He, Zeyu Shangguan, Kuanning Wang, Yongchong Gu, Yuqian Fu, Yanwei Fu, Daniel Seita

机构 * Thomas Lord Department of Computer Science, University of Southern California, USA（美国南加州大学计算机科学系）； Fudan University, China（复旦大学）； INSAIT, Sofia University “St. Kliment Ohridski”, Bulgaria（保加利亚索菲亚大学“圣克莱孟·奥赫里茨基”学院）

专题命中扩散模型：diffusion(abstract)

Comments Project Page: https://hesic73.github.io/SeqMultiGrasp/

2501.13655 2025-08-05 math.PR 50%

Linearization of ergodic McKean SDEs and applications

Grigorios A. Pavliotis, Andrea Zanoni

专题命中扩散模型：diffusion(abstract)

2501.10684 2025-08-05 cs.LG cs.CE stat.ML 50%

Deep Operator Networks for Bayesian Parameter Estimation in PDEs

Amogh Raj, Carol Eunice Gudumotou, Sakol Bun, Keerthana Srinivasa, Arash Sarshar

机构 * Department of Computer Engineering and Computer Science（计算机工程与计算机科学系）

专题命中扩散模型：diffusion(abstract)

2507.03257 2025-08-05 cs.CV 81%

LACONIC: A 3D Layout Adapter for Controllable Image Creation

Léopold Maillard, Tom Durand, Adrien Ramanana Rahary, Maks Ovsjanikov

机构 * LIX, École Polytechnique, IP Paris（巴黎高等理工学院LIX研究所）； Dassault Systèmes（达索系统）

专题命中可控生成：text-to-image(abstract)；diffusion(abstract)；image editing(abstract)；image synthesis(abstract)

Comments ICCV 2025

2508.01650 2025-08-05 cs.CV 57%

StrandDesigner: Towards Practical Strand Generation with Sketch Guidance

Na Zhang, Moran Li, Chengming Xu, Han Feng, Xiaobin Hu, Jiangning Zhang, Weijian Cao, Chengjie Wang, Yanwei Fu

机构 * Fudan University（复旦大学）； Tencent YouTu Lab（腾讯YouTu实验室）

专题命中可控生成：diffusion(abstract)；分类 cs.CV

Comments Accepted to ACM Multimedia 2025

2508.01152 2025-08-05 cs.CV 57%

LawDIS: Language-Window-based Controllable Dichotomous Image Segmentation

Xinyu Yan, Meijun Sun, Ge-Peng Ji, Fahad Shahbaz Khan, Salman Khan, Deng-Ping Fan

机构 * Tianjin University（天津大学）； Tianjin Key Laboratory of Machine Learning（天津机器学习重点实验室）； Australian National University（澳大利亚国立大学）； Nankai Institute of Advanced Research (SHENZHEN FUTIAN)（南开先进研究院（深圳福田））； Nankai University（南开大学）； MBZUAI

专题命中可控生成：diffusion(abstract)；分类 cs.CV

Comments 17 pages, 10 figures, ICCV 2025

2507.23309 2025-08-05 cs.CV 57%

PriorFusion: Unified Integration of Priors for Robust Road Perception in Autonomous Driving

Xuewei Tang, Mengmeng Yang, Tuopu Wen, Peijin Jia, Le Cui, Mingshang Luo, Kehua Sheng, Bo Zhang, Diange Yang, Kun Jiang

机构 * School of Vehicle and Mobility, Tsinghua University（车辆与移动系统学院，清华大学）

专题命中可控生成：diffusion(abstract)；分类 cs.CV

2507.00698 2025-08-05 cs.CV 57%

Rectifying Magnitude Neglect in Linear Attention

Qihang Fan, Huaibo Huang, Yuang Ai, Ran He

机构 * MAIS & NLPR, Institute of Automation, Chinese Academy of Sciences（自动化研究所）； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）

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

Comments Accepted by ICCV2025, highlight paper

2502.06957 2025-08-05 cs.CV 57%

GAS: Generative Avatar Synthesis from a Single Image

Yixing Lu, Junting Dong, Youngjoong Kwon, Qin Zhao, Bo Dai, Fernando De la Torre

机构 * Carnegie Mellon University（卡内基梅隆大学）； Shanghai AI Laboratory（上海人工智能实验室）； Stanford University（斯坦福大学）

专题命中可控生成：diffusion(abstract)；分类 cs.CV

Comments ICCV 2025; Project Page: https://humansensinglab.github.io/GAS/

2508.02093 2025-08-05 cs.AI 50%

"Stack It Up!": 3D Stable Structure Generation from 2D Hand-drawn Sketch

Yiqing Xu, Linfeng Li, Cunjun Yu, David Hsu

机构 * School of Computing（计算学院）； Smart Systems Institute（智能系统研究所）

专题命中可控生成：diffusion(abstract)

Comments Accepted to CoRL 2025

2508.01237 2025-08-05 cs.AI 50%

SketchAgent: Generating Structured Diagrams from Hand-Drawn Sketches

Cheng Tan, Qi Chen, Jingxuan Wei, Gaowei Wu, Zhangyang Gao, Siyuan Li, Bihui Yu, Ruifeng Guo, Stan Z. Li

机构 * Westlake University（西湖大学）； Zhejiang University（浙江大学）； University of Chinese Academy of Sciences（中国科学院大学）

专题命中可控生成：image generation(abstract)

Comments Accepted by IJCAI 2025

2501.18809 2025-08-05 cond-mat.soft 50%

Learning Continuum-level Closures For Control of Interacting Active Particles

Titus Quah, Sho C. Takatori, James B. Rawlings

专题命中可控生成：diffusion(abstract)

1. 扩散模型 70 篇

Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks

Progressive Growing of Video Tokenizers for Temporally Compact Latent Spaces

Virtual Staining of Label-Free Tissue in Imaging Mass Spectrometry

Abstract Formulation of Mean-Field Models and Propagation of Chaos

Why Generate When You Can Transform? Unleashing Generative Attention for Dynamic Recommendation

Frequency-Domain Denoising-Based in Vivo Fluorescence Imaging

On the Non-Markovian Navier-Stokes Framework for Turbulence Modeling -- A Preliminary Analysis

Enhancing Spectrogram Realism in Singing Voice Synthesis via Explicit Bandwidth Extension Prior to Vocoder

Dynamic Coupling of Infiltration-Soil Moisture Feedback:Emergent Vegetation Patterns in a Water-Vegetation Model

CLASS: Contrastive Learning via Action Sequence Supervision for Robot Manipulation

Sub 10 nm Nanochannels Enable Directional Quasi Ballistic Exciton Transport over 5 μm at Room Temperature

Viscosity Stabilized Plug-and-Play Reconstruction

Energy-dependent anisotropy of cosmic-ray muons: A twelve-year study with IceCube Neutrino Observatory

Time-resolved infrared photothermal imaging: From transient observations towards the steady-state

Stochastic Calculus Approach to Thermodynamics of Jump Processes

Approximate solutions to the shrinking core model and their interpretation

FloorPlan-DeepSeek (FPDS): A multimodal approach to floorplan generation using vector-based next room prediction

Asymptotic error distribution for stochastic Runge--Kutta methods of strong order one

Sequential Multi-Object Grasping with One Dexterous Hand

Linearization of ergodic McKean SDEs and applications

Deep Operator Networks for Bayesian Parameter Estimation in PDEs

2. 可控生成 10 篇

LACONIC: A 3D Layout Adapter for Controllable Image Creation

StrandDesigner: Towards Practical Strand Generation with Sketch Guidance

LawDIS: Language-Window-based Controllable Dichotomous Image Segmentation

PriorFusion: Unified Integration of Priors for Robust Road Perception in Autonomous Driving

Rectifying Magnitude Neglect in Linear Attention

GAS: Generative Avatar Synthesis from a Single Image

"Stack It Up!": 3D Stable Structure Generation from 2D Hand-drawn Sketch

SketchAgent: Generating Structured Diagrams from Hand-Drawn Sketches

Learning Continuum-level Closures For Control of Interacting Active Particles