arXiv周末暂无论文更新，休息一下吧，周末愉快~~

视觉与机器人

图像生成

图像生成、文生图、图像编辑、扩散模型和可控生成。

2025-09-29 至 2025-09-29 共收录 90 篇信号源：cs.CV, cs.GR, cs.MM

1. 扩散模型 57 篇

2412.07385 2025-09-29 cs.CV 79%

LOGen: Toward Lidar Object Generation by Point Diffusion

Ellington Kirby, Mickael Chen, Renaud Marlet, Nermin Samet

机构 * LIGM, Ecole des Ponts, Univ Gustave Eiffel, CNRS（LIGM，巴黎理工学院，埃菲尔大学，CNRS）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

Comments BMVC 2025

2405.10014 2025-09-29 cs.CV eess.IV 79%

Frequency-Domain Refinement with Multiscale Diffusion for Super Resolution

Xingjian Wang, Li Chai, Jiming Chen

机构 * Zhejiang University, College of Control Science and Engineering（浙江大学控制科学与工程学院）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2509.22519 2025-09-29 q-bio.PE 78%

A phenotype-structured reaction-diffusion model of avascular glioma growth

Francesca Ballatore, Xinran Ruan, Chiara Giverso, Tommaso Lorenzi

专题命中扩散模型：diffusion(title,abstract)

2509.22347 2025-09-29 quant-ph 78%

Decoding quantum low density parity check codes with diffusion

Zejun Liu, Anqi Gong, Bryan K. Clark

专题命中扩散模型：diffusion(title,abstract)

2509.22282 2025-09-29 cs.LG 78%

Conditional Denoising Diffusion Autoencoders for Wireless Semantic Communications

Mehdi Letafati, Samad Ali, Matti Latva-aho

机构 * Centre for Wireless Communications University of Oulu, Finland（无线通信中心奥卢大学，芬兰）

专题命中扩散模型：diffusion(title,abstract)

2509.22234 2025-09-29 math.AP 78%

The moving patch model with fractional diffusion

Sebastián Flores-Sepúlveda, Gabrielle Nornberg, Alexander Quaas

专题命中扩散模型：diffusion(title,abstract)

Comments 26 pages, 1 figure

2509.22038 2025-09-29 cs.LG cs.AI 78%

Latent Diffusion : Multi-Dimension Stable Diffusion Latent Space Explorer

Zhihua Zhong, Xuanyang Huang

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

专题命中扩散模型：diffusion(title,abstract)

2509.21942 2025-09-29 cs.LG 78%

Structural Information-based Hierarchical Diffusion for Offline Reinforcement Learning

Xianghua Zeng, Hao Peng, Angsheng Li, Yicheng Pan

机构 * State Key Laboratory of Software Development Environment（软件开发环境国家重点实验室）； Beihang University（北京航空航天大学）； Zhongguancun Laboratory（中关村实验室）

专题命中扩散模型：diffusion(title,abstract)

Comments Accepted by NeurIPS 2025

2509.21664 2025-09-29 cs.RO cs.LG 78%

Generating Stable Placements via Physics-guided Diffusion Models

Philippe Nadeau, Miguel Rogel, Ivan Bilić, Ivan Petrović, Jonathan Kelly

机构 * STARS Laboratory, University of Toronto Institute for Aerospace Studies（多伦多大学航空航天研究所STARS实验室）； Laboratory for Autonomous Systems and Mobile Robotics（自主系统与移动机器人实验室）； University of Zagreb Faculty of Electrical Engineering and Computing（Zagreb大学电气工程与计算学院）

专题命中扩散模型：diffusion(title,abstract)

Comments Submitted to the IEEE International Conference on Robotics and Automation 2026, Vienna, Austria, June 1-5, 2026

2509.21509 2025-09-29 quant-ph 78%

Quantum algorithms for solving a drift-diffusion equation: analysing circuit depths

Ellen Devereux, Animesh Datta

专题命中扩散模型：diffusion(title,abstract)

Comments 10 pages, 7 figures

2509.20253 2025-09-29 cs.RO cs.AI 78%

AnchDrive: Bootstrapping Diffusion Policies with Hybrid Trajectory Anchors for End-to-End Driving

Jinhao Chai, Anqing Jiang, Hao Jiang, Shiyi Mu, Zichong Gu, Hao Sun, Shugong Xu

机构 * School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China（信息工程学院，上海大学）； Bosch Corporate Research, Bosch (China) Investment Ltd., Shanghai, China（博世企业研究，博世（中国）投资有限公司）； School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China（机械工程学院，上海交通大学）； Xi'an Jiaotong-Liverpool University, Suzhou, China（西安交通大学利物浦大学）

专题命中扩散模型：diffusion(title,abstract)

2508.17379 2025-09-29 math.AP 78%

Stability and uniqueness of bounded weak solutions to triangular degenerate cross-diffusion systems

Xiuqing Chen, Bang Du, Ansgar Jüngel

专题命中扩散模型：diffusion(title,abstract)

2507.04504 2025-09-29 cs.CL 78%

Unveiling the Potential of Diffusion Large Language Model in Controllable Generation

Zhen Xiong, Yujun Cai, Zhecheng Li, Yiwei Wang

机构 * University of Southern California（南加州大学）； University of Queensland（昆士兰大学）； University of California, San Diego（加州大学圣地亚哥分校）； University of California, Merced（加州大学默塞德分校）

专题命中扩散模型：diffusion(title,abstract)

2506.06546 2025-09-29 cond-mat.mes-hall 78%

Orbital Hall conductivity and orbital diffusion length of Vanadium thin films by Hanle magnetoresistance

M. Xochitl Aguilar-Pujol, Isabel C. Arango, Eoin Dolan, You Ba, Marco Gobbi, Luis E. Hueso, Fèlix Casanova

专题命中扩散模型：diffusion(title,abstract)

Comments 14 pages, 5 figures, Supplemental Information

2505.16790 2025-09-29 cs.LG cs.AI 78%

Learning Flexible Forward Trajectories for Masked Molecular Diffusion

Hyunjin Seo, Taewon Kim, Sihyun Yu, SungSoo Ahn

专题命中扩散模型：diffusion(title,abstract)

2505.12230 2025-09-29 physics.comp-ph 78%

Predicting and understanding diffusion lengths and lifetimes in solids via a many-body \textit{ab initio} method: The role of coupled dynamics

Junqing Xu

专题命中扩散模型：diffusion(title,abstract)

Comments 7 pages, 3 figures

2502.04549 2025-09-29 cs.LG 78%

Mechanisms of Projective Composition of Diffusion Models

Arwen Bradley, Preetum Nakkiran, David Berthelot, James Thornton, Joshua M. Susskind

机构 * Apple, Cupertino, CA, USA（苹果公司）

专题命中扩散模型：diffusion(title,abstract)

Comments 10 pages, 8 figures. The first two authors contributed equally

2409.03636 2025-09-29 eess.AS 78%

ZSDEVC: Zero-Shot Diffusion-based Emotional Voice Conversion with Disentangled Mechanism

Hsing-Hang Chou, Yun-Shao Lin, Ching-Chin Sung, Yu Tsao, Chi-Chun Lee

专题命中扩散模型：diffusion(title,abstract)

Comments 5 pages; Proceedings of Interspeech

2406.02941 2025-09-29 math.NA cs.NA 78%

Numerical analysis of high-order methods for variable-exponent fractional diffusion-wave equation

Wenlin Qiu, Xiangcheng Zheng

专题命中扩散模型：diffusion(title,abstract)

2312.09830 2025-09-29 cs.LG cs.CE 78%

Data-Driven Socio-Economic Deprivation Prediction via Dimensionality Reduction: The Power of Diffusion Maps

June Moh Goo

机构 * Department of Civil, Environmental and Geomatics Engineering（土木、环境与测绘工程系）； University College London（伦敦大学学院）

专题命中扩散模型：diffusion(title,abstract)

Comments Accepted to 2024 IEEE International Conference on Big Data (IEEE Big Data 2024)

Journal ref 2024 IEEE International Conference on Big Data (BigData)

2509.21893 2025-09-29 cs.CV 74%

Syncphony: Synchronized Audio-to-Video Generation with Diffusion Transformers

Jibin Song, Mingi Kwon, Jaeseok Jeong, Youngjung Uh

机构 * Yonsei University（延世大学）

专题命中扩散模型：diffusion(title)；分类 cs.CV

Comments Project page: https://jibin86.github.io/syncphony_project_page

2312.04692 2025-09-29 cs.CR cs.CV cs.LG 74%

Diffence: Fencing Membership Privacy With Diffusion Models

Yuefeng Peng, Ali Naseh, Amir Houmansadr

机构 * University of Massachusetts Amherst（马萨诸塞大学阿姆赫斯特分校）

专题命中扩散模型：diffusion(title)；分类 cs.CV

Comments NDSS 2025

2509.22318 2025-09-29 cs.CV cs.LG 57%

NIFTY: a Non-Local Image Flow Matching for Texture Synthesis

Pierrick Chatillon, Julien Rabin, David Tschumperlé

机构 * Normandie Univ, UNICAEN, ENSICAEN, CNRS, GREYC（诺曼底大学、UNICAEN、ENSICAEN、CNRS、GREYC）

专题命中扩散模型：diffusion(abstract)；分类 cs.CV

2509.22112 2025-09-29 cs.CV 57%

Large Material Gaussian Model for Relightable 3D Generation

Jingrui Ye, Lingting Zhu, Runze Zhang, Zeyu Hu, Yingda Yin, Lanjiong Li, Lequan Yu, Qingmin Liao

机构 * Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）； The University of Hong Kong（香港大学）； LIGHTSPEED ； The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））

专题命中扩散模型：diffusion(abstract)；分类 cs.CV

2509.22070 2025-09-29 cs.CV 57%

SpecXNet: A Dual-Domain Convolutional Network for Robust Deepfake Detection

Inzamamul Alam, Md Tanvir Islam, Simon S. Woo

专题命中扩散模型：diffusion(abstract)；分类 cs.CV

Comments ACM MM Accepted

2509.22063 2025-09-29 cs.CV cs.SD 57%

High-Quality Sound Separation Across Diverse Categories via Visually-Guided Generative Modeling

Chao Huang, Susan Liang, Yapeng Tian, Anurag Kumar, Chenliang Xu

机构 * Meta Reality Labs Research（Meta现实实验室）

专题命中扩散模型：diffusion(abstract)；分类 cs.CV

Comments Accepted to IJCV

2509.21888 2025-09-29 cs.CV 57%

Drag4D: Align Your Motion with Text-Driven 3D Scene Generation

Minjun Kang, Inkyu Shin, Taeyeop Lee, In So Kweon, Kuk-Jin Yoon

机构 * KAIST（韩国科学技术院）； ByteDance Seed（字节跳动种子）

专题命中扩散模型：diffusion(abstract)；分类 cs.CV

Comments version 1

2509.21790 2025-09-29 cs.CV 57%

LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE

Yu Shang, Lei Jin, Yiding Ma, Xin Zhang, Chen Gao, Wei Wu, Yong Li

机构 * Tsinghua University（清华大学）； Manifold AI

专题命中扩散模型：diffusion(abstract)；分类 cs.CV

Comments 13 pages, 8 figures

2509.21760 2025-09-29 cs.CV 57%

UniVid: Unifying Vision Tasks with Pre-trained Video Generation Models

Lan Chen, Yuchao Gu, Qi Mao

机构 * MIPG, Communication University of China（信息与通信大学）； Show Lab, National University of Singapore（新加坡国立大学）

专题命中扩散模型：diffusion(abstract)；分类 cs.CV

2509.21574 2025-09-29 cs.CV 57%

X-Streamer: Unified Human World Modeling with Audiovisual Interaction

You Xie, Tianpei Gu, Zenan Li, Chenxu Zhang, Guoxian Song, Xiaochen Zhao, Chao Liang, Jianwen Jiang, Hongyi Xu, Linjie Luo

机构 * ByteDance（字节跳动）

专题命中扩散模型：diffusion(abstract)；分类 cs.CV

Comments Project Page at https://byteaigc.github.io/X-Streamer

↑