图像生成 - arXivDaily 专题

2510.08787 2025-10-13 cs.RO 50%

Geometry-aware Policy Imitation

Yiming Li, Nael Darwiche, Amirreza Razmjoo, Sichao Liu, Yilun Du, Auke Ijspeert, Sylvain Calinon

机构 * Idiap Research Institute（Idiap研究机构）； EPFL（瑞士联邦理工学院）； Harvard University（哈佛大学）

专题命中可控生成：diffusion(abstract)

Comments 21 pages, 13 figures. In submission

2509.20297 2025-10-08 cs.RO 50%

mindmap: Spatial Memory in Deep Feature Maps for 3D Action Policies

Remo Steiner, Alexander Millane, David Tingdahl, Clemens Volk, Vikram Ramasamy, Xinjie Yao, Peter Du, Soha Pouya, Shiwei Sheng

机构 * NVIDIA（英伟达）； Zurich Switzerland（苏黎世瑞士）； Santa Clara California（圣克拉拉加州）

专题命中可控生成：diffusion(abstract)

Comments Accepted to CoRL 2025 Workshop RemembeRL

2510.02148 2025-10-03 cs.LG 50%

Policy Gradient Guidance Enables Test Time Control

Jianing Qi, Hao Tang, Zhigang Zhu

机构 * CUNY Graduate Center（纽约大学研究生中心）； Borough of Manhattan Community College（曼哈顿社区学院）； The City College of New York（纽约城市大学）

专题命中可控生成：diffusion(abstract)

2510.01898 2025-10-03 math.PR 50%

A probabilistic representation for the gradient in a linear parabolic PDE with Neumann boundary condition

Abdelatif Benchérif Madani

专题命中可控生成：diffusion(abstract)

2509.25842 2025-10-01 cs.AI 50%

HiStyle: Hierarchical Style Embedding Predictor for Text-Prompt-Guided Controllable Speech Synthesis

Ziyu Zhang, Hanzhao Li, Jingbin Hu, Wenhao Li, Lei Xie

机构 * School of Computer Science, Northwestern Polytechnical University（计算机科学学院，西北工业大学）

专题命中可控生成：diffusion(abstract)

2509.25614 2025-10-01 math.PR math.OC 50%

Mean Field Type Control Problems Driven by Jump-diffusions

Alain Bensoussan, Ziyu Huang, Shanjian Tang, Sheung Chi Phillip Yam

专题命中可控生成：diffusion(abstract)

2509.23837 2025-09-30 eess.SY cs.SY 50%

Toward a Robust Biomimetic Hybrid Battery: Bridging Biology, Electrochemistry and Data-Driven Control

Raheel Ali, Rayid Ali

专题命中可控生成：diffusion(abstract)

2509.23590 2025-09-30 eess.IV eess.SP 50%

Foundation Model-Based Adaptive Semantic Image Transmission for Dynamic Wireless Environments

Fangyu Liu, Peiwen Jiang, Wenjin Wang, Chao-Kai Wen, Shi Jin, Jun Zhang

专题命中可控生成：diffusion(abstract)

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

2509.16041 2025-09-22 math.CA 50%

A Note on the formulation of the Neumann boundary condition for a nonlocal problem

Antonio Luiz Pereira

专题命中可控生成：diffusion(abstract)

Comments 12 pages, 1 figure

2509.15961 2025-09-22 cs.CE cs.NA math.NA 50%

Optimal Experimental Design of a Moving Sensor for Linear Bayesian Inverse Problems

Nicole Aretz, Thomas Lynn, Karen Willcox, Sven Leyffer

专题命中可控生成：diffusion(abstract)

2509.15934 2025-09-22 cs.LG 50%

UniTac2Pose: A Unified Approach Learned in Simulation for Category-level Visuotactile In-hand Pose Estimation

Mingdong Wu, Long Yang, Jin Liu, Weiyao Huang, Lehong Wu, Zelin Chen, Daolin Ma, Hao Dong

机构 * Center on Frontiers of Computing Studies, School of Computer Science, Peking University（前沿计算研究中心，计算机科学学院，北京大学）； PKU-AgiBot Lab（北京大学AGIBot实验室）； School of Ocean and Civil Engineering, Shanghai Jiao Tong University（海洋与ivil工程学院，上海交通大学）； Xense Robotics（Xense机器人）

专题命中可控生成：diffusion(abstract)

2509.14495 2025-09-19 math.OC 50%

A Time-Inconsistent Stochastic Optimal Control Problem in an Infinite Time Horizon

Qingmeng Wei, Jiongmin Yong

专题命中可控生成：diffusion(abstract)

2404.17236 2025-09-19 math.AP math.PR 50%

Stochastic optimal control problems with measurable coefficients and $L_d$-drift

David Criens

专题命中可控生成：diffusion(abstract)

Comments The paper is fully rewritten, covering more general settings with merely measurable coefficients, an $L_d$-drift and any dimension $d \geq 2$. Further, it discusses more cost functions and includes a discussion of the semigroup connection

2406.12945 2025-09-18 cs.LG stat.ML 50%

Tabular Data Generation Models: An In-Depth Survey and Performance Benchmarks with Extensive Tuning

G. Charbel N. Kindji, Lina Maria Rojas-Barahona, Elisa Fromont, Tanguy Urvoy

机构 * Univ Rennes, IUF, Inria, CNRS, IRISA（里昂大学、IUF、Inria、CNRS、IRISA）； Orange Labs（Orange实验室）

专题命中可控生成：diffusion(abstract)

2509.12528 2025-09-17 cond-mat.mes-hall physics.app-ph 50%

Topological Phononic Crystal on the Scale of Quasi-Ballistic Phonon Transport

Keita Funayama, Yuki Akura, Hiroya Tanaka, Jun Hirotani

专题命中可控生成：diffusion(abstract)

2509.09835 2025-09-15 math.OC math.PR 50%

A risk-sensitive ergodic singular stochastic control problem

Justin Gwee, Mihail Zervos

专题命中可控生成：diffusion(abstract)

2509.09499 2025-09-12 cs.IT math.IT 50%

Mixture of Semantics Transmission for Generative AI-Enabled Semantic Communication Systems

Junjie Ni, Tong Wu, Zhiyong Chen, Yin Xu, Meixia Tao, Wenjun Zhang

专题命中可控生成：diffusion(abstract)

Comments accepted by IEEE Communications Letters

2509.09269 2025-09-12 math.OC cs.SY eess.SY math.AP 50%

The role of communication delays in the optimal control of spatially invariant systems

Luca Ballotta, Juncal Arbelaiz, Vijay Gupta, Luca Schenato, Mihailo R. Jovanović

专题命中可控生成：diffusion(abstract)

Comments © 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

Journal ref IEEE Transactions on Automatic Control 2025

2509.09046 2025-09-12 cond-mat.stat-mech 50%

Noise-Activated Dopant Dynamics in Two-Dimensional Thermal Landscapes with Localized Cold Spots

Mesfin Taye, Yoseph Abebe, Tibebe Birhanu, Lemi Demeyu, Mulugeta Bekele

专题命中可控生成：diffusion(abstract)

Comments 8 pages, 5 figures

2403.16000 2025-09-12 math.OC math.PR 50%

Stochastic maximum principle for weighted mean-field system with jump

Yanyan Tang, Jie Xiong

专题命中可控生成：diffusion(abstract)

2310.12747 2025-09-12 math.AP 50%

Optimal decay rates to the contact wave for 1-D compressible Navier-Stokes equations

Lingjun Liu, Shu Wang, Lingda Xu

专题命中可控生成：diffusion(abstract)

2504.00238 2025-09-11 math.OC 50%

A Time-Reversal Control Synthesis for Steering the State of Stochastic Systems

Yuhang Mei, Amirhossein Taghvaei, Ali Pakniyat

专题命中可控生成：diffusion(abstract)

Comments 8 pages, 4 figures

2509.06217 2025-09-09 cond-mat.soft 50%

Multi-Scale Modeling and Predictive Control of Active Brownian Particles

Sadra Saremi, Amirhossein Ahmadkhan Kordbacheh

专题命中可控生成：diffusion(abstract)

2509.06201 2025-09-09 cs.RO cs.AI cs.LG 50%

Grasp-MPC: Closed-Loop Visual Grasping via Value-Guided Model Predictive Control

Jun Yamada, Adithyavairavan Murali, Ajay Mandlekar, Clemens Eppner, Ingmar Posner, Balakumar Sundaralingam

机构 * Applied AI Lab, Oxford Robotics Institute, University of Oxford（应用人工智能实验室、牛津机器人研究所、牛津大学）； NVIDIA, USA（NVIDIA公司）

专题命中可控生成：diffusion(abstract)

Comments 14 pages, 17 figures

2509.04992 2025-09-08 physics.flu-dyn 50%

Improving Spatial Resolution of Background Oriented Schlieren Based on Directional Rays

Xiang Li, Muen Gao, Weiran Wang, Jiawei Li, Chong Pan, Jinjun Wang, Yuan Xiong

专题命中可控生成：image generation(abstract)

2506.08570 2025-09-05 cs.SD cs.AI cs.LG eess.AS 50%

Auto-Regressive vs Flow-Matching: a Comparative Study of Modeling Paradigms for Text-to-Music Generation

Or Tal, Felix Kreuk, Yossi Adi

机构 * The Hebrew University（希伯来大学）； Meta Fundamental AI Research（Meta 基础人工智能研究）

专题命中可控生成：inpainting(abstract)

2507.10578 2025-09-04 cs.CR cs.AI 50%

When and Where do Data Poisons Attack Textual Inversion?

Jeremy Styborski, Mingzhi Lyu, Jiayou Lu, Nupur Kapur, Adams Kong

机构 * College of Computing and Data Science, Nanyang Technological University, Singapore（计算与数据科学学院，南洋理工大学，新加坡）； Rapid-Rich Object Search (ROSE) Lab, Nanyang Technological University, Singapore（快速丰富对象搜索（ROSE）实验室，南洋理工大学，新加坡）

专题命中可控生成：diffusion(abstract)

Comments Accepted to ICCV 2025

2507.11156 2025-09-03 astro-ph.EP astro-ph.SR 50%

Hydrodynamical simulations of the vertical shear instability with dynamic dust and cooling rates in protoplanetary disks

Yuya Fukuhara, Mario Flock, Satoshi Okuzumi, Ryosuke T. Tominaga

专题命中可控生成：diffusion(abstract)

Comments 16 pages, 20 figures, 1 table, Accepted for publication in Astronomy & Astrophysics (A&A)

Journal ref A&A 701, A72 (2025)

2412.20519 2025-09-03 cs.LG cs.AI cs.RO 50%

Goal-Conditioned Data Augmentation for Offline Reinforcement Learning

Xingshuai Huang, Di Wu, Benoit Boulet

机构 * McGill University（麦吉尔大学）

专题命中可控生成：diffusion(abstract)

1. 可控生成 4236 篇

Geometry-aware Policy Imitation

mindmap: Spatial Memory in Deep Feature Maps for 3D Action Policies

Policy Gradient Guidance Enables Test Time Control

A probabilistic representation for the gradient in a linear parabolic PDE with Neumann boundary condition

HiStyle: Hierarchical Style Embedding Predictor for Text-Prompt-Guided Controllable Speech Synthesis

Mean Field Type Control Problems Driven by Jump-diffusions

Toward a Robust Biomimetic Hybrid Battery: Bridging Biology, Electrochemistry and Data-Driven Control

Foundation Model-Based Adaptive Semantic Image Transmission for Dynamic Wireless Environments

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

A Note on the formulation of the Neumann boundary condition for a nonlocal problem

Optimal Experimental Design of a Moving Sensor for Linear Bayesian Inverse Problems

UniTac2Pose: A Unified Approach Learned in Simulation for Category-level Visuotactile In-hand Pose Estimation

A Time-Inconsistent Stochastic Optimal Control Problem in an Infinite Time Horizon

Stochastic optimal control problems with measurable coefficients and $L_d$-drift

Tabular Data Generation Models: An In-Depth Survey and Performance Benchmarks with Extensive Tuning

Topological Phononic Crystal on the Scale of Quasi-Ballistic Phonon Transport

A risk-sensitive ergodic singular stochastic control problem

Mixture of Semantics Transmission for Generative AI-Enabled Semantic Communication Systems

The role of communication delays in the optimal control of spatially invariant systems

Noise-Activated Dopant Dynamics in Two-Dimensional Thermal Landscapes with Localized Cold Spots

Stochastic maximum principle for weighted mean-field system with jump

Optimal decay rates to the contact wave for 1-D compressible Navier-Stokes equations

A Time-Reversal Control Synthesis for Steering the State of Stochastic Systems

Multi-Scale Modeling and Predictive Control of Active Brownian Particles

Grasp-MPC: Closed-Loop Visual Grasping via Value-Guided Model Predictive Control

Improving Spatial Resolution of Background Oriented Schlieren Based on Directional Rays

Auto-Regressive vs Flow-Matching: a Comparative Study of Modeling Paradigms for Text-to-Music Generation

When and Where do Data Poisons Attack Textual Inversion?

Hydrodynamical simulations of the vertical shear instability with dynamic dust and cooling rates in protoplanetary disks

Goal-Conditioned Data Augmentation for Offline Reinforcement Learning