图像生成

2509.17020 2025-09-23 math.NA cs.NA 50%

Multiscale solution decomposition of nonlocal-in-time problems with application in numerical computation

Mengmeng Liu, Jie Ma, Wenlin Qiu, Xiangcheng Zheng

专题命中扩散模型：diffusion(abstract)

2509.16842 2025-09-23 stat.ML cs.LG stat.ME 50%

DoubleGen: Debiased Generative Modeling of Counterfactuals

Alex Luedtke, Kenji Fukumizu

机构 * Harvard University（哈佛大学）； Institute of Statistical Mathematics（统计数学研究所）

专题命中扩散模型：diffusion(abstract)

Comments Keywords: generative modeling, counterfactual, doubly robust, debiased machine learning

2509.15952 2025-09-23 cs.SD cs.AI cs.LG eess.AS 50%

Compose Yourself: Average-Velocity Flow Matching for One-Step Speech Enhancement

Gang Yang, Yue Lei, Wenxin Tai, Jin Wu, Jia Chen, Ting Zhong, Fan Zhou

机构 * University of Electronic Science and Technology of China（电子科技大学）

专题命中扩散模型：diffusion(abstract)

Comments 5 pages, 2 figures, submitted to ICASSP 2026

2509.13113 2025-09-23 physics.flu-dyn 50%

Spatiotemporally Resolved Measurements of CO2 Distribution at the Air-Water Interface Using Tunable Diode Laser Spectroscopy

Dongfang Zhao, Yumin Shi, Shengkai Wang

专题命中扩散模型：diffusion(abstract)

2508.01500 2025-09-23 nlin.AO physics.soc-ph 50%

The role of zealots in the spread of linguistic traits

Vivian Dornelas, Celia Anteneodo, Renan Nunes, Els Heinsalu, Marco Patriarca

专题命中扩散模型：diffusion(abstract)

Comments 13 pages with 10 figures

2507.03009 2025-09-23 cs.CL cs.IR cs.LG 50%

PDFMathTranslate: Scientific Document Translation Preserving Layouts

Rongxin Ouyang, Chang Chu, Zhikuang Xin, Xiangyao Ma

机构 * National University of Singapore（新加坡国立大学）； Tsinghua University（清华大学）； University of Chinese Academy of Sciences（中国科学院大学）； Funstory.ai Limited（Funstory.ai有限公司）

专题命中扩散模型：diffusion(abstract)

Comments 7 pages, 4 figures, EMNLP 2025 System Demonstration

2504.17532 2025-09-23 cond-mat.mtrl-sci 50%

Permeation and thermal desorption model of hydrogen in steel: a sensitivity analysis

Paolo Emilio Di Nunzio

专题命中扩散模型：diffusion(abstract)

Comments The paper needs substantial revisions that cannot be implemented at the moment

2504.17022 2025-09-23 cs.ET 50%

Molecular Communication Channel as a Physical Reservoir Computer

Mustafa Uzun, Kaan Burak Ikiz, Murat Kuscu

专题命中扩散模型：diffusion(abstract)

2408.13851 2025-09-23 math.CA 50%

Flow of the zeros of polynomials under iterated differentiation

Andrei Martinez-Finkelshtein, Evgenii A. Rakhmanov

专题命中扩散模型：diffusion(abstract)

Comments 28 pages; to appear in Analysis & PDE

2403.01240 2025-09-23 hep-ph hep-th nucl-th 50%

Analyzing the transport coefficients and observables of a rotating QGP medium in kinetic theory framework with a novel approach to the collision integral

Shubhalaxmi Rath, Sadhana Dash

专题命中扩散模型：diffusion(abstract)

Comments 32 pages, 9 figures

2509.16385 2025-09-23 q-bio.PE stat.AP 50%

Parameter variability can produce heavy tails in a model for the spatial distribution of settling organisms

Luis F. Gordillo, Priscilla E. Greenwood

专题命中扩散模型：diffusion(abstract)

2509.16357 2025-09-23 cs.LG 50%

Guided Sequence-Structure Generative Modeling for Iterative Antibody Optimization

Aniruddh Raghu, Sebastian Ober, Maxwell Kazman, Hunter Elliott

机构 * BigHat Biosciences（BigHat生物技术公司）； University of Washington（华盛顿大学）

专题命中扩散模型：diffusion(abstract)

Comments GEM Workshop, ICLR 2025

2509.10218 2025-09-23 astro-ph.EP 50%

Ionospheric Electron Heat Flow Modulates Planetary Ambipolar Electric Fields

Liangliang Yuan, Shuanggen Jin

专题命中扩散模型：diffusion(abstract)

2505.03432 2025-09-23 cs.LG math.OC math.PR stat.ML 50%

Wasserstein Convergence of Score-based Generative Models under Semiconvexity and Discontinuous Gradients

Stefano Bruno, Sotirios Sabanis

机构 * School of Mathematics University of Edinburgh, United Kingdom（爱丁堡大学数学学院）； Department of Industrial Engineering Ulsan National Institute of Science and Technology, Republic of Korea（釜山国立科学技术院工业工程系）； National Technical University of Athens, Greece（雅典国家技术大学）； Archimedes, Athena Research Center, Greece（阿提卡研究中心）

专题命中扩散模型：diffusion(abstract)

Comments Accepted for publication in Transactions on Machine Learning Research

2506.23711 2025-09-23 cs.CV 79%

Subjective Camera 1.0: Bridging Human Cognition and Visual Reconstruction through Sequence-Aware Sketch-Guided Diffusion

Haoyang Chen, Dongfang Sun, Caoyuan Ma, Shiqin Wang, Kewei Zhang, Zheng Wang, Zhixiang Wang

机构 * National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, School of Computer Science, Wuhan University（国家多媒体软件工程研究中心，人工智能研究院，计算机科学学院，武汉大学）； Hubei Key Laboratory of Multimedia and Network Communication Engineering（湖北省多媒体与网络通信工程重点实验室）； Zhongguancun Academy, Beijing, China（中关村学院，北京，中国）； CyberAgent AI Lab, Japan（CyberAgent AI实验室，日本）

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

2509.17757 2025-09-23 cs.CV cs.MA 77%

Multi-Agent Amodal Completion: Direct Synthesis with Fine-Grained Semantic Guidance

Hongxing Fan, Lipeng Wang, Haohua Chen, Zehuan Huang, Jiangtao Wu, Lu Sheng

机构 * School of Computer Science and Engineering（计算机科学与工程学院）； Beihang University（北京航空航天大学）； School of Software（软件学院）

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

2506.16806 2025-09-23 cs.CV 77%

FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation

Fan Yang, Yousong Zhu, Xin Li, Yufei Zhan, Hongyin Zhao, Shurong Zheng, Yaowei Wang, Ming Tang, Jinqiao Wang

机构 * Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所基础模型研究中心）； School of Artificial Intelligence, University of Chinese Academy of Science（中国科学院大学人工智能学院）； Peng Cheng Laboratory, Shenzhen, China（鹏城实验室）； Wuhan AI Research, Wuhan, China（武汉人工智能研究所）

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

2509.17476 2025-09-23 cs.CV 57%

Stable Video-Driven Portraits

Mallikarjun B. R., Fei Yin, Vikram Voleti, Nikita Drobyshev, Maksim Lapin, Aaryaman Vasishta, Varun Jampani

机构 * Stability AI ； University of Cambridge（剑桥大学）； Cantina

专题命中可控生成：diffusion(abstract)；分类 cs.CV

Comments https://stable-video-driven-portraits.github.io/

2509.16550 2025-09-23 cs.RO cs.AI cs.SY eess.SY 50%

TranTac: Leveraging Transient Tactile Signals for Contact-Rich Robotic Manipulation

Yinghao Wu, Shuhong Hou, Haowen Zheng, Yichen Li, Weiyi Lu, Xun Zhou, Yitian Shao

机构 * School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Shenzhen, China（计算机科学与技术学院，哈尔滨工业大学深圳校区）； State Key Laboratory of Smart Farm Technologies and Systems, Harbin, China（智能农业技术与系统国家重点实验室，哈尔滨，中国）

专题命中可控生成：diffusion(abstract)

Comments 8 pages, 7 figures

2509.17022 2025-09-23 cs.MM cs.CV cs.SD eess.AS 81%

VAInpaint: Zero-Shot Video-Audio inpainting framework with LLMs-driven Module

Kam Man Wu, Zeyue Tian, Liya Ji, Qifeng Chen

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学）

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

2509.17120 2025-09-23 cs.CV 70%

Stencil: Subject-Driven Generation with Context Guidance

Gordon Chen, Ziqi Huang, Cheston Tan, Ziwei Liu

专题命中个性化与一致性：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments Accepted as Spotlight at ICIP 2025

Journal ref Proc. IEEE Int. Conf. Image Process. (ICIP), Anchorage, AK, USA, Sept. 14-17, 2025, pp. 719-724

2509.17088 2025-09-23 cs.CV 70%

AlignedGen: Aligning Style Across Generated Images

Jiexuan Zhang, Yiheng Du, Qian Wang, Weiqi Li, Yu Gu, Jian Zhang

机构 * School of Electronic and Computer Engineering, Peking University（电子与计算机工程学院，北京大学）

专题命中个性化与一致性：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

2509.17219 2025-09-23 cs.SD cs.LG 50%

Virtual Consistency for Audio Editing

Matthieu Cervera, Francesco Paissan, Mirco Ravanelli, Cem Subakan

机构 * 1 Mila-Qu\'ebec AI Institute, 2 Laval University, 3 Concordia University, 4 University of Montreal

专题命中个性化与一致性：diffusion(abstract)

2412.07435 2025-09-23 cs.DS cs.DC cs.LG cs.NA math.NA 71%

Parallel Simulation for Log-concave Sampling and Score-based Diffusion Models

Huanjian Zhou, Masashi Sugiyama

机构 * Center for Advanced Intelligence Project, RIKEN（RIKEN先进人工智能项目中心）； The University of Tokyo（东京大学）

专题命中效率与蒸馏：diffusion(title)

Comments Accepted to ICML2025 and this version corrects errors from the previous submission

2509.16630 2025-09-23 cs.CV 57%

Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation

Yue Ma, Zexuan Yan, Hongyu Liu, Hongfa Wang, Heng Pan, Yingqing He, Junkun Yuan, Ailing Zeng, Chengfei Cai, Heung-Yeung Shum, Zhifeng Li, Wei Liu, Linfeng Zhang, Qifeng Chen

机构 * HKUST（香港科技大学）； SJTU（上海交通大学）； Tencent（腾讯）

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

Comments accepted by IJCV2025. project page:https://follow-your-emoji.github.io

2509.14847 2025-09-23 math.NA cs.NA 50%

A class of flexible and efficient partitioned Runge-Kutta-Chebyshev methods for some time-dependent partial differential equations

Xiao Tang, Junwei Huang

专题命中效率与蒸馏：diffusion(abstract)

2509.16363 2025-09-23 cs.CV 74%

Introducing Resizable Region Packing Problem in Image Generation, with a Heuristic Solution

Hrishikesh Sharma

机构 * TCS Research（TCS研究）

专题命中其他图像生成：image generation(title)；分类 cs.CV

2002.04112 2025-09-23 cs.GT cs.LG 50%

Connecting GANs, MFGs, and OT

Haoyang Cao, Xin Guo, Mathieu Laurière

专题命中其他图像生成：image generation(abstract)

Comments Previous version was under the title "Connecting GANs and MFGs"

1. 扩散模型 69 篇

Multiscale solution decomposition of nonlocal-in-time problems with application in numerical computation

DoubleGen: Debiased Generative Modeling of Counterfactuals

Compose Yourself: Average-Velocity Flow Matching for One-Step Speech Enhancement

Spatiotemporally Resolved Measurements of CO2 Distribution at the Air-Water Interface Using Tunable Diode Laser Spectroscopy

The role of zealots in the spread of linguistic traits

PDFMathTranslate: Scientific Document Translation Preserving Layouts

Permeation and thermal desorption model of hydrogen in steel: a sensitivity analysis

Molecular Communication Channel as a Physical Reservoir Computer

Flow of the zeros of polynomials under iterated differentiation

Analyzing the transport coefficients and observables of a rotating QGP medium in kinetic theory framework with a novel approach to the collision integral

Parameter variability can produce heavy tails in a model for the spatial distribution of settling organisms

Guided Sequence-Structure Generative Modeling for Iterative Antibody Optimization

Ionospheric Electron Heat Flow Modulates Planetary Ambipolar Electric Fields

Wasserstein Convergence of Score-based Generative Models under Semiconvexity and Discontinuous Gradients

2. 可控生成 5 篇

Subjective Camera 1.0: Bridging Human Cognition and Visual Reconstruction through Sequence-Aware Sketch-Guided Diffusion

Multi-Agent Amodal Completion: Direct Synthesis with Fine-Grained Semantic Guidance

FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation

Stable Video-Driven Portraits

TranTac: Leveraging Transient Tactile Signals for Contact-Rich Robotic Manipulation

3. 图像修复 1 篇

VAInpaint: Zero-Shot Video-Audio inpainting framework with LLMs-driven Module

4. 个性化与一致性 3 篇

Stencil: Subject-Driven Generation with Context Guidance

AlignedGen: Aligning Style Across Generated Images

Virtual Consistency for Audio Editing

5. 效率与蒸馏 3 篇

Parallel Simulation for Log-concave Sampling and Score-based Diffusion Models

Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation

A class of flexible and efficient partitioned Runge-Kutta-Chebyshev methods for some time-dependent partial differential equations

6. 其他图像生成 2 篇

Introducing Resizable Region Packing Problem in Image Generation, with a Heuristic Solution

Connecting GANs, MFGs, and OT