图像生成

Using Node Centrality and Optimal Control to Maximize Information Diffusion in Social Networks

利用节点中心性与最优控制最大化社交网络中的信息扩散

Kundan Kandhway, Joy Kuri

专题命中 可控生成 ：diffusion(title)

AI总结 本文研究如何通过节点中心性与最优控制策略优化信息在社交网络中的扩散，比较不同中心性指标的效果，并验证在资源有限时优先选择中心节点的策略。

Comments 12 pages, 11 figures. Author's version of an article published in IEEE Transactions on Systems, Man, and Cybernetics: Systems. Minor typos were fixed in v2. The published version can be accessed at http://dx.doi.org/10.1109/TSMC.2016.2531690

Journal ref IEEE Transactions on Systems, Man, and Cybernetics: Systems, Volume: 47, Issue: 7, Pages 1099-1110, July 2017

Consensus-based control for a network of diffusion PDEs with boundary local interaction

基于共识的扩散PDE网络边界局部交互控制

A. Pilloni, A. Pisano, Y. Orlov, E. Usai

专题命中 可控生成 ：diffusion(title)

AI总结 本文提出基于共识的控制方法，用于驱动由边界控制热方程建模的网络状态趋同于共同稳态分布。采用分布式共识协议解决两个问题：一是使所有代理状态趋同于初始条件的空间平均稳态分布，二是处理边界扰动下的同步问题。

Utility-Aware Multimodal Contrastive Learning for Product Image Generation

效用感知的多模态对比学习用于产品图像生成

Xiaohang Feng, Yiling Xie

机构 * City University of Hong Kong（香港城市大学） 纠错

专题命中 可控生成 ：image generation(title)

AI总结 提出一种效用感知的多模态对比学习框架，通过引入效用感知InfoNCE损失优化产品图像生成，使图像在语义对齐的同时提升市场需求。

Cross-Layer Isochronous Diffusion Protocol (CIDP): A Rigorous Information-Theoretic and Control-Theoretic Framework for Sovereign Tactical Anonymity

跨层等时扩散协议（CIDP）：一种严格的信息论和控制论框架，用于主权战术匿名性

Pravin G

专题命中 可控生成 ：diffusion(title)

AI总结 CIDP通过物理层熵注入和控制理论框架，实现强匿名性、低延迟和低带宽开销的平衡，适用于主权战术网络的JADC2部署。

Comments 11 pages, 4 figures, 4 tables, with full proofs and FPGA prototype evaluation

MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control

Yuchen Zhu, Wei Guo, Jaemoo Choi, Guan-Horng Liu, Yongxin Chen, Molei Tao

机构 * Georgia Institute of Technology（佐治亚理工学院） ； FAIR at Meta（Meta的FAIR） 纠错

专题命中 可控生成 ：diffusion(title)

Comments NeurIPS 2025

BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling

Hao Li, Yu-Hao Huang, Chang Xu, Viktor Schlegel, Renhe Jiang, Riza Batista-Navarro, Goran Nenadic, Jiang Bian

机构 * Microsoft Research（微软研究院） ； The University of Manchester, UK（英国曼彻斯特大学） ； Nanjing University, China（南京大学） ； Imperial College London, Imperial Global Singapore, Singapore（伦敦帝国学院，新加坡帝国全球分校，新加坡） ； The University of Tokyo, Japan（日本东京大学） 纠错

专题命中 可控生成 ：diffusion(title)

Comments ICML 2025 Main Conference

Structure-Preserving Medical Image Generation from a Latent Graph Representation

Kevin Arias, Edwin Vargas, Kumar Vijay Mishra, Antonio Ortega, Henry Arguello

专题命中 可控生成 ：image generation(title)

Stochastic Optimal Control with Control-Dependent Diffusion and State Constraints: A Degenerate Elliptic Approach

Anderson O. Calixto, Bernardo Freitas Paulo da Costa, Glauco Valle

专题命中 可控生成 ：diffusion(title)

Comments 22 pages. arXiv admin note: substantial text overlap with arXiv:2505.14987

TrajDiff: Diffusion Bridge Network with Semantic Alignment for Trajectory Similarity Computation

Xiao Zhang, Xingyu Zhao, Hong Xia, Yuan Cao, Guiyuan Jiang, Junyu Dong, Yanwei Yu

机构 * Faculty of Information Science and Engineering（信息科学与工程学院） 纠错

专题命中 可控生成 ：diffusion(title)

EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models

Che Hyun Lee, Heeseung Kim, Jiheum Yeom, Sungroh Yoon

机构 * Department of Electrical and Computer Engineering, Seoul National University（电子与计算机工程系，首尔国立大学） ； AIIS, ASRI, INMC, ISRC, and IPAI, Seoul National University（人工智能研究所、先进系统研究室、智能网络中心、信息科学研究中心和人工智能计划，首尔国立大学） 纠错

专题命中 可控生成 ：diffusion(title)

Comments ACL 2025

Birth control and turnpike property of Lotka-McKendrick models with diffusion

Marius Bargo, Yacouba Simpore

专题命中 可控生成 ：diffusion(title)

Comments https://doi.org/10.48550/arXiv.2408.05291

LACE: Exploring Turn-Taking and Parallel Interaction Modes in Human-AI Co-Creation for Iterative Image Generation

YenKai Huang, Zheng Ning, Ming Cheng

专题命中 可控生成 ：image generation(title)

Comments Extended version of the short paper accepted at the GenAICHI Workshop at CHI 2025. Includes additional results, analysis, qualitative feedback, and discussion

Multiple Ultrasound Image Generation based on Tuned Alignment of Amplitude Hologram over Spatially non-Uniform Ultrasound Source

Keisuke Hasegawa

专题命中 可控生成 ：image generation(title)

Adaptive Compliance Policy: Learning Approximate Compliance for Diffusion Guided Control

Yifan Hou, Zeyi Liu, Cheng Chi, Eric Cousineau, Naveen Kuppuswamy, Siyuan Feng, Benjamin Burchfiel, Shuran Song

专题命中 可控生成 ：diffusion(title)

Deep Generalized Schrödinger Bridges: From Image Generation to Solving Mean-Field Games

Guan-Horng Liu, Tianrong Chen, Evangelos A. Theodorou

专题命中 可控生成 ：image generation(title)

ControlMol: Adding Substructure Control To Molecule Diffusion Models

Qi Zhengyang, Liu Zijing, Zhang Jiying, Cao He, Li Yu

专题命中 可控生成 ：diffusion(title)

Comments 5 pages,3 figures

Optimal control of diffusion processes: $\infty$-order variational analysis and numerical solution

Roman Chertovskih, Nikolay Pogodaev, Maxim Staritsyn, A. Pedro Aguiar

专题命中 可控生成 ：diffusion(title)

Journal ref IEEE Control Systems Letters, vol. 8, pp. 1469-1474, 2024

Enhanced control of single-molecule emission frequency and spectral diffusion

Rocco Duquennoy, Simon Landrieux, Daniele De Bernardis, Juergen Mony, Maja Colautti, Lin Jin, Wolfram H. P. Pernice, Costanza Toninelli

专题命中 可控生成 ：diffusion(title)

CoLay: Controllable Layout Generation through Multi-conditional Latent Diffusion

Chin-Yi Cheng, Ruiqi Gao, Forrest Huang, Yang Li

专题命中 可控生成 ：diffusion(title)

VulMCI : Code Splicing-based Pixel-row Oversampling for More Continuous Vulnerability Image Generation

Tao Peng, Ling Gui, Yi Sun

专题命中 可控生成 ：image generation(title)

Dynamics of a memory-based diffusion model with spatial heterogeneity and nonlinear boundary condition

Quanli Ji, Ranchao Wu, Tonghua Zhang

专题命中 可控生成 ：diffusion(title)

TypeDance: Creating Semantic Typographic Logos from Image through Personalized Generation

Shishi Xiao, Liangwei Wang, Xiaojuan Ma, Wei Zeng

专题命中 可控生成 ：personalized generation(title)

Comments 24 pages, 9 figures

T-FOLEY: A Controllable Waveform-Domain Diffusion Model for Temporal-Event-Guided Foley Sound Synthesis

Yoonjin Chung, Junwon Lee, Juhan Nam

专题命中 可控生成 ：diffusion(title)

Audio Generation with Multiple Conditional Diffusion Model

Zhifang Guo, Jianguo Mao, Rui Tao, Long Yan, Kazushige Ouchi, Hong Liu, Xiangdong Wang

专题命中 可控生成 ：diffusion(title)

Comments Accepted by AAAI 2024

Stability of FFLS-based diffusion adaptive filter under a cooperative excitation condition

Die Gan, Siyu Xie, Zhixin Liu, Jinhu Lv

专题命中 可控生成 ：diffusion(title)

Comments 12 pages

Control of fractional diffusion problems via dynamic programming equations

Alessandro Alla, Marta D'Elia, Christian Glusa, Hugo Oliveira

专题命中 可控生成 ：diffusion(title)

Optimal Control of Diffusion Processes with Terminal Constraint in Law

Samuel Daudin

专题命中 可控生成 ：diffusion(title)

Deterministic Control of Stochastic Reaction-Diffusion Equations

Wilhelm Stannat, Lukas Wessels

专题命中 可控生成 ：diffusion(title)

Comments accepted for publication in Evolution Equations & Control Theory; 21 pages, 10 figures

Journal ref Evol. Equ. Control Theory, 10 (2021), 701-722

Control and numerical approximation of fractional diffusion equations

Umberto Biccari, Mahamadi Warma, Enrique Zuazua

专题命中 可控生成 ：diffusion(title)

Optimal control of a 2D diffusion-advection process with a team of mobile actuators under jointly optimal guidance

Sheng Cheng, Derek A. Paley

专题命中 可控生成 ：diffusion(title)

Comments Proofs for Lemmas~2.3, 2.5, and D.1 are attached in the supplement at the end