图像生成

DocDjinn: Controllable Synthetic Document Generation with VLMs and Handwriting Diffusion

DocDjinn: 基于VLMs和手写扩散的可控合成文档生成

Marcel Lamott, Saifullah Saifullah, Nauman Riaz, Yves-Noel Weweler, Tobias Alt-Veit, Ahmad Sarmad Ali, Muhammad Armaghan Shakir, Adrian Kalwa, Momina Moetesum, Andreas Dengel, Sheraz Ahmed, Faisal Shafait, Ulrich Schwanecke, Adrian Ulges

机构 * RheinMain University of Applied Sciences（莱茵-美因应用科学大学） ； German Research Center for Artificial Intelligence（德国人工智能研究中心） ； DeepReader GmbH（DeepReader公司） ； Insiders Technologies GmbH（Insiders Technologies公司） ； National University of Sciences and Technology（国家科学与技术大学） 纠错

专题命中 可控生成 ：diffusion(title,abstract)

AI总结 DocDjinn利用VLMs和手写扩散生成可控合成文档，通过聚类和参数化采样从未标注种子生成高质量标注文档，实现隐私保护和高效数据生成。

DegDiT: Controllable Audio Generation with Dynamic Event Graph Guided Diffusion Transformer

DegDiT：基于动态事件图引导的扩散变换器的可控音频生成

Yisu Liu, Chenxing Li, Wanqian Zhang, Wenfu Wang, Meng Yu, Ruibo Fu, Zheng Lin, Weiping Wang, Dong Yu

机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院） ； Tencent, AI Lab（腾讯AI实验室） ； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） 纠错

专题命中 可控生成 ：diffusion(title,abstract)

AI总结 DegDiT通过动态事件图引导的扩散变换器框架，实现了开放式词汇可控音频生成，提升了生成音频的准确性和多样性。

Journal ref IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2026

Generative Modeling of Human-Computer Interfaces with Diffusion Processes and Conditional Control

基于扩散过程和条件控制的人机界面生成模型

Rui Liu, Liuqingqing Yang, Runsheng Zhang, Shixiao Wang

专题命中 可控生成 ：diffusion(title,abstract)

AI总结 本文提出基于扩散过程和条件控制的界面生成模型，通过整合用户意图和任务约束，提升界面生成的多样性、合理性和智能化。

Coarse-Grained Kullback--Leibler Control of Diffusion-Based Generative AI

粗粒度Kullback-Leibler控制的扩散基生成AI

Tatsuaki Tsuruyama

机构 * Department of Physics, Tohoku University（东大理学部） ； Department of Drug Discovery Medicine, Kyoto University（京都大学药学部） 纠错

专题命中 可控生成 ：diffusion(title,abstract)

AI总结 本文提出了一种基于V-delta势能的反向扩散方案，通过控制粗粒度量来提升生成图像的质量和稳定性。

Numerical analysis of a stabilized scheme for an optimal control problem governed by a parabolic convection--diffusion equation

对由抛物型对流-扩散方程所支配的最优控制问题的稳定化方案的数值分析

Christos Pervolianakis

专题命中 可控生成 ：diffusion(title,abstract)

AI总结 本文研究了由抛物型对流-扩散方程支配的最优控制问题，提出稳定化方案并推导了误差估计，通过数值实验验证了其收敛性。

Audio Palette: A Diffusion Transformer with Multi-Signal Conditioning for Controllable Foley Synthesis

音频调色盘：一种多信号条件的扩散变压器用于可控的 Foley 合成

Junnuo Wang

机构 * New York University（纽约大学） 纠错

专题命中 可控生成 ：diffusion(title,abstract)

AI总结 Audio Palette通过多信号条件和LoRA技术实现可控Foley合成，提供高效、可解释的音频生成与控制方法。

Comments Accepted for publication in the Artificial Intelligence Technology Research (AITR)

When Motion Learns to Listen: Diffusion-Prior Lyapunov Actor-Critic Framework with LLM Guidance for Stable and Robust AUV Control in Underwater Tasks

当运动学会倾听：带有LLM引导的扩散先验Lyapunov动作-批评者框架用于水下任务中稳定和鲁棒的AUV控制

Jingzehua Xu, Weiyi Liu, Weihang Zhang, Zhuofan Xi, Guanwen Xie, Shuai Zhang, Yi Li

专题命中 可控生成 ：diffusion(title,abstract)

AI总结 本文提出一种结合扩散模型、Lyapunov批评者和LLM的框架，用于提升水下机器人控制的稳定性与鲁棒性，通过生成-过滤-优化机制实现高效探索和多目标优化。

Comments This paper is currently under review and does not represent the final version. Jingzehua Xu, Weiyi Liu and Weihang Zhang are co-first authors of this paper, with Zhuofan Xi as the second author

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)

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

CtrlDiff: Boosting Large Diffusion Language Models with Dynamic Block Prediction and Controllable Generation

Chihan Huang, Hao Tang

机构 * Nanjing University of Science and Technology（南京理工大学） ； Peking University（北京大学） 纠错

专题命中 可控生成 ：diffusion(title,abstract)

Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control

Chengxiu Hua, Jiawen Gu, Yushun Tang

机构 * Southern University of Science and Technology（南方科技大学） ； Huawei Technologies Co., Ltd（华为技术有限公司） 纠错

专题命中 可控生成 ：diffusion(title,abstract)

Canvas3D: Empowering Precise Spatial Control for Image Generation with Constraints from a 3D Virtual Canvas

Runlin Duan, Yuzhao Chen, Rahul Jain, Yichen Hu, Jingyu Shi, Karthik Ramani

专题命中 可控生成 ：image generation(title,abstract)

Control Copy-Paste: Controllable Diffusion-Based Augmentation Method for Remote Sensing Few-Shot Object Detection

Yanxing Liu, Jiancheng Pan, Bingchen Zhang

专题命中 可控生成 ：diffusion(title,abstract)

Comments 5 Pages, 3 figures

Image Generation with Supervised Selection Based on Multimodal Features for Semantic Communications

Chengyang Liang, Dong Li

专题命中 可控生成 ：image generation(title)；diffusion(abstract)

Deep learning-based Fast Volumetric Image Generation for Image-guided Proton FLASH Radiotherapy

Chih-Wei Chang, Yang Lei, Tonghe Wang, Sibo Tian, Justin Roper, Liyong Lin, Jeffrey Bradley, Tian Liu, Jun Zhou, Xiaofeng Yang

专题命中 可控生成 ：image generation(title,abstract)

Journal ref IEEE Transactions on Radiation and Plasma Medical Sciences, vol. 8, no. 8, pp. 973-983, Nov. 2024

Toward Near-Globally Optimal Nonlinear Model Predictive Control via Diffusion Models

Tzu-Yuan Huang, Armin Lederer, Nicolas Hoischen, Jan Brüdigam, Xuehua Xiao, Stefan Sosnowski, Sandra Hirche

专题命中 可控生成 ：diffusion(title,abstract)

Comments This paper has been accepted by the 2025 7th Annual Learning for Dynamics & Control Conference (L4DC) as an oral presentation and has been nominated for the best paper award

Towards Sustainable Creativity Support: An Exploratory Study on Prompt Based Image Generation

Daniel Hove Paludan, Julie Fredsgård, Kasper Patrick Bährentz, Ilhan Aslan, Niels van Berkel

专题命中 可控生成 ：image generation(title,abstract)

Comments 20 pages, 8 figures

Optimal control of the fidelity coefficient in a Cahn-Hilliard image inpainting model

Elena Beretta, Cecilia Cavaterra, Matteo Fornoni, Maurizio Grasselli

专题命中 可控生成 ：inpainting(title,abstract)

Comments 40 pages, revised version, to appear in ESAIM: Control Optim. Calc. Var

A Note on Semantic Diffusion

Alexander P. Ryjov, Alina A. Egorova

专题命中 可控生成 ：diffusion(title,abstract)

Comments 8 figures

SPOT: SE(3) Pose Trajectory Diffusion for Object-Centric Manipulation

Cheng-Chun Hsu, Bowen Wen, Jie Xu, Yashraj Narang, Xiaolong Wang, Yuke Zhu, Joydeep Biswas, Stan Birchfield

机构 * NVIDIA ； University of Texas at Austin（德克萨斯大学奥斯汀分校） ； University of California San Diego（加州大学圣地亚哥分校） 纠错

专题命中 可控生成 ：diffusion(title,abstract)

Quantum Generative Learning for High-Resolution Medical Image Generation

Amena Khatun, Kübra Yeter Aydeniz, Yaakov S. Weinstein, Muhammad Usman

专题命中 可控生成 ：image generation(title,abstract)

Journal ref Mach. Learn.: Sci. Technol. 6 025032, 2025

Task-Adaptive Semantic Communications with Controllable Diffusion-based Data Regeneration

Fupei Guo, Achintha Wijesinghe, Songyang Zhang, Zhi Ding

机构 * University of Louisiana at Lafayette（路易斯安那大学拉斐特分校） ； University of California at Davis（加州大学戴维斯分校） 纠错

专题命中 可控生成 ：diffusion(title,abstract)

Enhancing Product Search Interfaces with Sketch-Guided Diffusion and Language Agents

Edward Sun

专题命中 可控生成 ：diffusion(title,abstract)

Comments Companion Proceedings of the ACM Web Conference 2025

Stochastic scattering control of spider diffusion governed by an optimal diffraction probability measure selected from its own local-time

Isaac Ohavi

专题命中 可控生成 ：diffusion(title,abstract)

Comments 53 pages

Diffusion-Based Imitation Learning for Social Pose Generation

Antonio Lech Martin-Ozimek, Isuru Jayarathne, Su Larb Mon, Jouh Yeong Chew

专题命中 可控生成 ：diffusion(title,abstract)

Comments This paper was submitted as an LBR to HRI2025

Text Semantics to Flexible Design: A Residential Layout Generation Method Based on Stable Diffusion Model

Zijin Qiu, Jiepeng Liu, Yi Xia, Hongtuo Qi, Pengkun Liu

专题命中 可控生成 ：diffusion(title,abstract)

Editing Music with Melody and Text: Using ControlNet for Diffusion Transformer

Siyuan Hou, Shansong Liu, Ruibin Yuan, Wei Xue, Ying Shan, Mangsuo Zhao, Chao Zhang

专题命中 可控生成 ：diffusion(title,abstract)

Comments Accepted for publication at ICASSP 2025

CASC: Condition-Aware Semantic Communication with Latent Diffusion Models

Weixuan Chen, Qianqian Yang

专题命中 可控生成 ：diffusion(title,abstract)

The Role of Domain Randomization in Training Diffusion Policies for Whole-Body Humanoid Control

Oleg Kaidanov, Firas Al-Hafez, Yusuf Suvari, Boris Belousov, Jan Peters

专题命中 可控生成 ：diffusion(title,abstract)

Comments Conference on Robot Learning, Workshop on Whole-Body Control and Bimanual Manipulation

SC-CDM: Enhancing Quality of Image Semantic Communication with a Compact Diffusion Model

Kexin Zhang, Lixin Li, Wensheng Lin, Yuna Yan, Wenchi Cheng, Zhu Han

专题命中 可控生成 ：diffusion(title,abstract)

Comments arXiv admin note: text overlap with arXiv:2408.05112