图像生成

2510.27331 2025-11-03 math.AP 50%

Instantaneous Total Enhanced Dissipation For Very Rough Shear Flows

Marco Romito, Leonardo Roveri

专题命中扩散模型：diffusion(abstract)

2510.27303 2025-11-03 math.PR math.DS 50%

The memory-dependent FPK equation for fractional Gaussian noise

Lifang Feng, Bin Pei, Yong Xu

专题命中扩散模型：diffusion(abstract)

Comments Accepted by Probabilistic Engineering Mechanics

2510.27165 2025-11-03 cs.SI 50%

Structure-Aware Optimal Intervention for Rumor Dynamics on Networks: Node-Level, Time-Varying, and Resource-Constrained

Yan Zhu, Qingyang Liu, Chang Guo, Tianlong Fan, Linyuan Lü

专题命中扩散模型：diffusion(abstract)

Comments 32 pages,3 figures

2510.26973 2025-11-03 astro-ph.SR 50%

Zeeman Doppler mapping deconstructed

M. J. Stift, F. Leone

专题命中扩散模型：diffusion(abstract)

Comments 10 pages, 13 figures

2510.26928 2025-11-03 physics.med-ph physics.app-ph physics.bio-ph physics.chem-ph 50%

Ultra-High Dose-Rates, the FLASH Effect, and Hydrogen Peroxide Yields: Do Experiments and Simulations Really Disagree?

Marc Benjamin Hahn

专题命中扩散模型：diffusion(abstract)

Comments 16 pages

2510.26906 2025-11-03 cond-mat.str-el cond-mat.dis-nn physics.comp-ph 50%

Enhancing Neural Network Backflow

Kieran Loehr, Bryan K. Clark

专题命中扩散模型：diffusion(abstract)

Comments 11 pages, 8 figures

2510.26897 2025-11-03 cond-mat.stat-mech cond-mat.str-el quant-ph 50%

Superdiffusion and anomalous fluctuations in chiral integrable dynamics

Cristiano Muzzi, Devendra Singh Bhakuni, Marcello Dalmonte, Lenart Zadnik, Hernan B. Xavier

专题命中扩散模型：diffusion(abstract)

Comments 12 pages, 4 figures

2510.24944 2025-11-03 math.NA cs.NA 50%

Interpolated Discrepancy Data Assimilation for PDEs with Sparse Observations

Tong Wu, Humberto Godinez, Vitaliy Gyrya, James M. Hyman

专题命中扩散模型：diffusion(abstract)

Comments 25 pages, 6 figures, submitted to SIAM Journal on Scientific Computing (SISC)

2506.15121 2025-11-03 cond-mat.stat-mech cs.NE 50%

Generative thermodynamic computing

Stephen Whitelam

专题命中扩散模型：diffusion(abstract)

2506.11420 2025-11-03 cs.LG cs.CE 50%

PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design

Zhenqiao Song, Tiaoxiao Li, Lei Li, Martin Renqiang Min

机构 * Language Technologies Institute, Carnegie Mellon University（卡内基梅隆大学语言技术研究所）； NEC Laboratories America（日本电报电话公司美洲实验室）

专题命中扩散模型：diffusion(abstract)

2504.02721 2025-11-03 math.DS cs.NA math-ph math.MP math.NA math.PR 50%

Phase transitions for interacting particle systems on random graphs

Benedetta Bertoli, Grigorios A. Pavliotis, Niccolò Zagli

专题命中扩散模型：diffusion(abstract)

Comments 27 pages, 5 figures

2410.08309 2025-11-03 cs.LG stat.ML 50%

Swing-by Dynamics in Concept Learning and Compositional Generalization

Yongyi Yang, Core Francisco Park, Ekdeep Singh Lubana, Maya Okawa, Wei Hu, Hidenori Tanaka

机构 * CBS-NTT Physics of Intelligence Program, Harvard University（哈佛大学）； Physics & Informatics Laboratories, NTT Research, Inc.（NTT研究公司）； Computer Science and Engineering, University of Michigan（密歇根大学）； Department of Physics, Harvard University（哈佛大学）

专题命中扩散模型：diffusion(abstract)

2407.03334 2025-11-03 math.NA cs.NA 50%

Linear model reduction using spectral proper orthogonal decomposition

Peter Frame, Cong Lin, Oliver Schmidt, Aaron Towne

专题命中扩散模型：diffusion(abstract)

Comments 38 pages, 17 figures

Journal ref Computer Methods in Applied Mechanics and Engineering, Vol. 447, Article 118382 (2025)

2510.27169 2025-11-03 cs.CV 79%

DANCER: Dance ANimation via Condition Enhancement and Rendering with diffusion model

Yucheng Xing, Jinxing Yin, Xiaodong Liu

机构 * Stony Brook University（石溪大学）

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

2510.27555 2025-11-03 math.AP 78%

On the global existence and uniform-in-time bounds for three-component reaction-diffusion systems with mass control and polynomial growth

Redouane Douaifia, Salem Abdelmalek, Mokhtar Kirane

专题命中可控生成：diffusion(title,abstract)

2509.24591 2025-11-03 cs.RO cs.AI 78%

PoseDiff: A Unified Diffusion Model Bridging Robot Pose Estimation and Video-to-Action Control

Haozhuo Zhang, Michele Caprio, Jing Shao, Qiang Zhang, Jian Tang, Shanghang Zhang, Wei Pan

专题命中可控生成：diffusion(title,abstract)

Comments The experimental setup and metrics lacks rigor, affecting the fairness of the comparisons

2510.27324 2025-11-03 cs.CV cs.AI 70%

Generative Semantic Coding for Ultra-Low Bitrate Visual Communication and Analysis

Weiming Chen, Yijia Wang, Zhihan Zhu, Zhihai He

机构 * Southern University of Science and Technology, Shenzhen, China（南方科技大学）

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

2510.27452 2025-11-03 cs.CV 57%

From Pixels to Paths: A Multi-Agent Framework for Editable Scientific Illustration

Jianwen Sun, Fanrui Zhang, Yukang Feng, Chuanhao Li, Zizhen Li, Jiaxin Ai, Yifan Chang, Yu Dai, Kaipeng Zhang

机构 * Nankai University（南开大学）； Shanghai Innovation Institute（上海创新研究院）； Wuhan University（武汉大学）； University of Science and Technology of China（中国科学技术大学）； Shanghai AI Laboratory（上海人工智能实验室）

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

2510.18637 2025-11-03 cs.CV cs.AI cs.LG 57%

ε-Seg: Sparsely Supervised Semantic Segmentation of Microscopy Data

Sheida Rahnamai Kordasiabi, Damian Dalle Nogare, Florian Jug

机构 * Human Technopole, Milan, Italy（米兰人类技术极地）； Technical University of Dresden, Germany（德累斯顿技术大学）

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

Comments 10 pages main text, 17 pages total

2407.16407 2025-11-03 math.OC cs.LG cs.SY eess.SY stat.ML 50%

Data-Driven Stochastic Optimal Control in Reproducing Kernel Hilbert Spaces

Nicolas Hoischen, Petar Bevanda, Stefan Sosnowski, Sandra Hirche, Boris Houska

机构 * School of Information Science and Technology, ShanghaiTech University（信息科学与技术学院，上海科技大学）

专题命中可控生成：diffusion(abstract)

Comments author-submitted electronic preprint version: 19 pages, 5 figures, 3 tables

2407.15395 2025-11-03 eess.SP 50%

FAST: Flexible and Adaptive Semantic Transmission for Resource-constrained Multi-user Generative Semantic Communication

Yiru Wang, Wanting Yang, Fangli Mou, Zehui Xiong, Zide Fan, Shiwen Mao, Tony Q. S. Quek

专题命中可控生成：diffusion(abstract)

2510.27364 2025-11-03 cs.CV cs.AI 57%

Fine-Tuning Open Video Generators for Cinematic Scene Synthesis: A Small-Data Pipeline with LoRA and Wan2.1 I2V

Meftun Akarsu, Kerem Catay, Sedat Bin Vedat, Enes Kutay Yarkan, Ilke Senturk, Arda Sar, Dafne Eksioglu

机构 * AI Yapım Hagia Labs Singapore（AI Yapım 赫亚实验室新加坡）； AI Engineer Hagia Labs İstanbul（AI工程师赫亚实验室伊斯坦布尔）； Full Stack Engineer Hagia Labs İstanbul（全栈工程师赫亚实验室伊斯坦布尔）； Chief Creator Hagia Labs İstanbul（首席创作者赫亚实验室伊斯坦布尔）

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

Comments video generation, image-to-video, dif- fusion transformer, LoRA, fine-tuning, cinematic scene synthesis, multi-GPU inference, fully sharded data parallelism, computational efficiency

2404.15743 2025-11-03 cs.CV 57%

SRAGAN: Saliency Regularized and Attended Generative Adversarial Network for Chinese Ink-wash Painting Style Transfer

Xiang Gao, Yuqi Zhang

机构 * Wangxuan Institute of Computer Technology, Peking University（北京大学王轩计算机技术研究所）； School of Mathematical Sciences, University of Chinese Academy of Sciences（中国科学院大学数学科学学院）

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

Comments Pattern Recognition, Volume 162, June 2025, 111344

Journal ref Pattern Recognition, 2025, 162: 111344

2510.27671 2025-11-03 cs.AI cs.LG 50%

MolChord: Structure-Sequence Alignment for Protein-Guided Drug Design

Wei Zhang, Zekun Guo, Yingce Xia, Peiran Jin, Shufang Xie, Tao Qin, Xiang-Yang Li

机构 * School of Computer Science and Technology, University of Science and Technology of China（1 计算机科学与技术学院，中国科学技术大学）； Zhongguancun Academy（2 中关村学院）

专题命中图像生成评测：diffusion(abstract)

Comments 21 pages

2510.23285 2025-11-03 cs.CV 79%

Adaptive Stochastic Coefficients for Accelerating Diffusion Sampling

Ruoyu Wang, Beier Zhu, Junzhi Li, Liangyu Yuan, Chi Zhang

机构 * AGI Lab, Westlake University（西交大实验室，西湖大学）； Nanyang Technological University（南洋理工大学）； University of Chinese Academy of Sciences（中国科学院大学）； Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）； Tongji University（同济大学）

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

Comments To appear in NeurIPS 2025

2510.26892 2025-11-03 cs.LG cs.AI 50%

BI-DCGAN: A Theoretically Grounded Bayesian Framework for Efficient and Diverse GANs

Mahsa Valizadeh, Rui Tuo, James Caverlee

专题命中效率与蒸馏：diffusion(abstract)

2506.15653 2025-11-03 cond-mat.stat-mech physics.chem-ph 50%

Fokker-Planck Score Learning: Efficient Free-Energy Estimation under Periodic Boundary Conditions

Daniel Nagel, Tristan Bereau

专题命中效率与蒸馏：diffusion(abstract)

Comments 11 pages, 4 figures

2504.15827 2025-11-03 cs.LG cs.AI 50%

DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers

Xuyang Zhong, Haochen Luo, Chen Liu

专题命中其他图像生成：image generation(abstract)

1. 扩散模型 39 篇

Instantaneous Total Enhanced Dissipation For Very Rough Shear Flows

The memory-dependent FPK equation for fractional Gaussian noise

Structure-Aware Optimal Intervention for Rumor Dynamics on Networks: Node-Level, Time-Varying, and Resource-Constrained

Zeeman Doppler mapping deconstructed

Ultra-High Dose-Rates, the FLASH Effect, and Hydrogen Peroxide Yields: Do Experiments and Simulations Really Disagree?

Enhancing Neural Network Backflow

Superdiffusion and anomalous fluctuations in chiral integrable dynamics

Interpolated Discrepancy Data Assimilation for PDEs with Sparse Observations

Generative thermodynamic computing

PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design

Phase transitions for interacting particle systems on random graphs

Swing-by Dynamics in Concept Learning and Compositional Generalization

Linear model reduction using spectral proper orthogonal decomposition

2. 可控生成 8 篇

DANCER: Dance ANimation via Condition Enhancement and Rendering with diffusion model

On the global existence and uniform-in-time bounds for three-component reaction-diffusion systems with mass control and polynomial growth

PoseDiff: A Unified Diffusion Model Bridging Robot Pose Estimation and Video-to-Action Control

Generative Semantic Coding for Ultra-Low Bitrate Visual Communication and Analysis

From Pixels to Paths: A Multi-Agent Framework for Editable Scientific Illustration

ε-Seg: Sparsely Supervised Semantic Segmentation of Microscopy Data

Data-Driven Stochastic Optimal Control in Reproducing Kernel Hilbert Spaces

FAST: Flexible and Adaptive Semantic Transmission for Resource-constrained Multi-user Generative Semantic Communication

3. 个性化与一致性 2 篇

Fine-Tuning Open Video Generators for Cinematic Scene Synthesis: A Small-Data Pipeline with LoRA and Wan2.1 I2V

SRAGAN: Saliency Regularized and Attended Generative Adversarial Network for Chinese Ink-wash Painting Style Transfer

4. 图像生成评测 1 篇

MolChord: Structure-Sequence Alignment for Protein-Guided Drug Design

5. 效率与蒸馏 3 篇

Adaptive Stochastic Coefficients for Accelerating Diffusion Sampling

BI-DCGAN: A Theoretically Grounded Bayesian Framework for Efficient and Diverse GANs

Fokker-Planck Score Learning: Efficient Free-Energy Estimation under Periodic Boundary Conditions

6. 其他图像生成 1 篇

DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers