图像生成

2510.00383 2025-10-02 physics.flu-dyn physics.ao-ph 50%

Generative AI for subgrid turbulence in large-eddy simulations

Yu Cheng, Tianle Liu

专题命中扩散模型：diffusion(abstract)

Comments 18 pages, 4 figures

2510.00367 2025-10-02 stat.ML cs.LG math.ST stat.ME stat.TH 50%

CINDES: Classification induced neural density estimator and simulator

Dehao Dai, Jianqing Fan, Yihong Gu, Debarghya Mukherjee

专题命中扩散模型：diffusion(abstract)

Comments 50 pages, 1 figure

2510.00351 2025-10-02 cs.LG q-bio.BM 50%

Flow Autoencoders are Effective Protein Tokenizers

Rohit Dilip, Evan Zhang, Ayush Varshney, David Van Valen

机构 * California Institute of Technology（加州理工学院）； OpenAI（开放人工智能公司）； Howard Hughes Medical Institute（霍华德·休斯医学研究院）

专题命中扩散模型：diffusion(abstract)

2510.00297 2025-10-02 math.OC cs.LG 50%

Malliavin Calculus with Weak Derivatives for Counterfactual Stochastic Optimization

Vikram Krishnamurthy, Luke Snow

机构 * School of Electrical and Computer Engineering, Cornell University（电气与计算机工程学院，康奈尔大学）

专题命中扩散模型：diffusion(abstract)

2510.00173 2025-10-02 math.AP 50%

Stackelberg-Nash strategy for the null controllability of semilinear degenerate equations in non-cylindrical domains

Alfredo S. Gamboa, Juan Limaco, Luis P. Yapu

专题命中扩散模型：diffusion(abstract)

Comments arXiv admin note: text overlap with arXiv:2509.19505

2510.00087 2025-10-02 stat.AP cs.LG math.PR q-bio.QM 50%

Revealing the temporal dynamics of antibiotic anomalies in the infant gut microbiome with neural jump ODEs

Anja Adamov, Markus Chardonnet, Florian Krach, Jakob Heiss, Josef Teichmann, Nicholas A. Bokulich

专题命中扩散模型：diffusion(abstract)

2509.18811 2025-10-02 cs.LG physics.ao-ph 50%

Training-Free Data Assimilation with GenCast

Thomas Savary, François Rozet, Gilles Louppe

机构 * ENS Paris-Saclay（巴黎-萨克雷大学）； University of Liège（列日大学）

专题命中扩散模型：diffusion(abstract)

2506.04103 2025-10-02 math.AP 50%

Global convergence rates in the relaxation limits for the compressible Euler and Euler-Maxwell systems in Sobolev spaces

Timothée Crin-Barat, Yue-Jun Peng, Ling-Yun Shou

专题命中扩散模型：diffusion(abstract)

Comments 47 pages

2401.10179 2025-10-02 math.PR math.DS 50%

An Invariance Principle for a Random Walk Among Moving Traps via Thermodynamic Formalism

Siva Athreya, Alexander Drewitz, Rongfeng Sun

专题命中扩散模型：diffusion(abstract)

Comments 42 pages. To appear in Commun. Math. Phys

2303.07859 2025-10-02 cond-mat.soft physics.chem-ph 50%

Poisson-Nernst-Planck charging dynamics of an electric double layer capacitor: symmetric and asymmetric binary electrolytes

Ivan Palaia, Adelchi J. Asta, Megh Dutta, Patrick B. Warren, Benjamin Rotenberg, Emmanuel Trizac

专题命中扩散模型：diffusion(abstract)

Journal ref Phys. Rev. E 112, 035417 (2025)

2503.13434 2025-10-02 cs.CV cs.AI cs.MM 84%

BlobCtrl: Taming Controllable Blob for Element-level Image Editing

Yaowei Li, Lingen Li, Zhaoyang Zhang, Xiaoyu Li, Guangzhi Wang, Hongxiang Li, Xiaodong Cun, Ying Shan, Yuexian Zou

机构 * SECE, Peking University（北京大学SECE学院）； The Chinese University of Hong Kong（香港中文大学）； ARC Lab, Tencent（腾讯ARC实验室）； The Hong Kong University of Science and Technology（香港科学与技术大学）； GVC Lab, Great Bay University（Great Bay大学GVC实验室）

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

Comments Project Webpage: https://liyaowei-stu.github.io/project/BlobCtrl/ This version presents a major update with rephrased writing. Accepted to SIGGRAPH Asia 2025

2510.00820 2025-10-02 cs.CV 70%

NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution

Xiangtao Kong, Rongyuan Wu, Shuaizheng Liu, Lingchen Sun, Lei Zhang

机构 * The Hong Kong Polytechnic University（香港理工大学）； OPPO Research Institute（OPPO研究院）

专题命中图像修复：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

2510.00047 2025-10-02 cs.CV cs.AI 57%

Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model Explanations

Sihao Ding, Santosh Vasa, Aditi Ramadwar

机构 * Mercedes-Benz Research & Development North America（梅赛德斯-奔驰研究与开发北美）

专题命中图像修复：inpainting(abstract)；分类 cs.CV

Comments NeurIPS 2025 workshop on Regulatable ML

2510.00437 2025-10-02 math.OC 50%

A primal-dual splitting algorithm with convex combination and larger step sizes for composite monotone inclusion problems

Xiaokai Chang, Junfeng Yang, Jianchao Bai, Jianxiong Cao

专题命中图像修复：inpainting(abstract)

Comments 30 pages

Journal ref published in SIAM Journal on Imaging Sciences,2025

2510.00658 2025-10-02 cs.CV cs.AI cs.LG 57%

Align Your Tangent: Training Better Consistency Models via Manifold-Aligned Tangents

Beomsu Kim, Byunghee Cha, Jong Chul Ye

机构 * Graduate School of AI, KAIST（人工智能研究生院，韩国科学技术院）

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

Comments Preprint

2510.00633 2025-10-02 cs.CV cs.LG 57%

Virtual Fashion Photo-Shoots: Building a Large-Scale Garment-Lookbook Dataset

Yannick Hauri, Luca A. Lanzendörfer, Till Aczel

机构 * ETH Zurich（苏黎世联邦理工学院）

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

2510.00006 2025-10-02 cs.SD cs.CL cs.CY cs.MM eess.AS 57%

Unpacking Musical Symbolism in Online Communities: Content-Based and Network-Centric Approaches

Kajwan Ziaoddini

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

2412.07754 2025-10-02 cs.CV cs.AI cs.LG 57%

PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation

Fatemeh Nazarieh, Zhenhua Feng, Diptesh Kanojia, Muhammad Awais, Josef Kittler

机构 * School of Computer Science and Electronic Engineering, University of Surrey（计算机科学与电子工程系，塞夫顿大学）； Centre for Vision, Speech and Signal Processing, University of Surrey（视觉、语音与信号处理中心，塞夫顿大学）； School of Artificial Intelligence and Computer Science, Jiangnan University（人工智能与计算机科学系，江南大学）

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

2507.12142 2025-10-02 cs.LG cs.CL cs.NA math.DG math.NA 50%

LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters

Vladimir Bogachev, Vladimir Aletov, Alexander Molozhavenko, Denis Bobkov, Vera Soboleva, Aibek Alanov, Maxim Rakhuba

机构 * HSE University（俄罗斯高等经济大学）

专题命中个性化与一致性：diffusion(abstract)

2510.00627 2025-10-02 cs.AI 78%

Collaborative-Distilled Diffusion Models (CDDM) for Accelerated and Lightweight Trajectory Prediction

Bingzhang Wang, Kehua Chen, Yinhai Wang

机构 * Department of Civil and Environmental Engineering, University of Washington（华盛顿大学土木与环境工程系）

专题命中效率与蒸馏：diffusion(title,abstract)

2510.01061 2025-10-02 cs.GR cs.CV cs.LG 62%

ReSWD: ReSTIR'd, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction

Mark Boss, Andreas Engelhardt, Simon Donné, Varun Jampani

机构 * Stability AI ； University of Tübingen（图宾根大学）

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

2510.00624 2025-10-02 cs.CV 57%

UCD: Unconditional Discriminator Promotes Nash Equilibrium in GANs

Mengfei Xia, Nan Xue, Jiapeng Zhu, Yujun Shen

机构 * Ant Group（蚂蚁集团）

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

2510.00260 2025-10-02 cs.LG cs.AI cs.CV 57%

Learning Energy-based Variational Latent Prior for VAEs

Debottam Dutta, Chaitanya Amballa, Zhongweiyang Xu, Yu-Lin Wei, Romit Roy Choudhury

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

2410.02367 2025-10-02 cs.LG 50%

SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

Jintao Zhang, Jia Wei, Haofeng Huang, Pengle Zhang, Jun Zhu, Jianfei Chen

机构 * Dept. of Comp. Sci. & Tech.（计算机科学与技术系）； Institute for AI（人工智能研究院）； BNRist Center（BNRist中心）； Tsinghua-Bosch Joint ML Center（清华大学-博世联合机器学习中心）； THBI Lab（THBI实验室）； Tsinghua University（清华大学）

专题命中效率与蒸馏：image generation(abstract)

Comments @inproceedings{zhang2025sageattention, title={SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration}, author={Zhang, Jintao and Wei, Jia and Zhang, Pengle and Zhu, Jun and Chen, Jianfei}, booktitle={International Conference on Learning Representations (ICLR)}, year={2025} }

Journal ref The Thirteenth International Conference on Learning Representations (ICLR 2025)

2510.00722 2025-10-02 math.NA cs.NA 50%

Carleman Linearization of Parabolic PDEs: Well-posedness, convergence, and efficient numerical methods

Bernhard Heinzelreiter, John W. Pearson

专题命中效率与蒸馏：diffusion(abstract)

Comments 32 pages

1. 扩散模型 34 篇

Generative AI for subgrid turbulence in large-eddy simulations

CINDES: Classification induced neural density estimator and simulator

Flow Autoencoders are Effective Protein Tokenizers

Malliavin Calculus with Weak Derivatives for Counterfactual Stochastic Optimization

Stackelberg-Nash strategy for the null controllability of semilinear degenerate equations in non-cylindrical domains

Revealing the temporal dynamics of antibiotic anomalies in the infant gut microbiome with neural jump ODEs

Training-Free Data Assimilation with GenCast

Global convergence rates in the relaxation limits for the compressible Euler and Euler-Maxwell systems in Sobolev spaces

An Invariance Principle for a Random Walk Among Moving Traps via Thermodynamic Formalism

Poisson-Nernst-Planck charging dynamics of an electric double layer capacitor: symmetric and asymmetric binary electrolytes

2. 可控生成 1 篇

BlobCtrl: Taming Controllable Blob for Element-level Image Editing

3. 图像修复 3 篇

NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution

Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model Explanations

A primal-dual splitting algorithm with convex combination and larger step sizes for composite monotone inclusion problems

4. 个性化与一致性 5 篇

Align Your Tangent: Training Better Consistency Models via Manifold-Aligned Tangents

Virtual Fashion Photo-Shoots: Building a Large-Scale Garment-Lookbook Dataset

Unpacking Musical Symbolism in Online Communities: Content-Based and Network-Centric Approaches

PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation

LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters

5. 效率与蒸馏 6 篇

Collaborative-Distilled Diffusion Models (CDDM) for Accelerated and Lightweight Trajectory Prediction

ReSWD: ReSTIR'd, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction

UCD: Unconditional Discriminator Promotes Nash Equilibrium in GANs

Learning Energy-based Variational Latent Prior for VAEs

SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

Carleman Linearization of Parabolic PDEs: Well-posedness, convergence, and efficient numerical methods