图像生成

Melodia: Training-Free Music Editing Guided by Attention Probing in Diffusion Models

Yi Yang, Haowen Li, Tianxiang Li, Boyu Cao, Xiaohan Zhang, Liqun Chen, Qi Liu

专题命中 扩散模型 ：diffusion(title,abstract)

Comments AAAI 2026 (Oral)

Drift-diffusion equations with saturation

José Antonio Carrillo, Alejandro Fernández-Jiménez, David Gómez-Castro

专题命中 扩散模型 ：diffusion(title)

Comments 52 pages, 7 figures

Unlocking the Forgery Detection Potential of Vanilla MLLMs: A Novel Training-Free Pipeline

Rui Zuo, Qinyue Tong, Zhe-Ming Lu, Ziqian Lu

机构 * Zhejiang University（浙江大学） ； Zhejiang Sci-Tech University（浙江科技学院） 纠错

专题命中 扩散模型 ：image generation(abstract)；diffusion(abstract)；分类 cs.CV

Zero-shot Synthetic Video Realism Enhancement via Structure-aware Denoising

Yifan Wang, Liya Ji, Zhanghan Ke, Harry Yang, Ser-Nam Lim, Qifeng Chen

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学） ； Everlyn AI ； University of Central Florida（中央佛罗里达大学） 纠错

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

Comments Project Page: https://wyf0824.github.io/Video_Realism_Enhancement/

Text-Driven Reasoning Video Editing via Reinforcement Learning on Digital Twin Representations

Yiqing Shen, Chenjia Li, Mathias Unberath

机构 * Department of Computer Science, Johns Hopkins University（计算机科学系，约翰霍普金斯大学） 纠错

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

Single Tensor Cell Segmentation using Scalar Field Representations

Kevin I. Ruiz Vargas, Gabriel G. Galdino, Tsang Ing Ren, Alexandre L. Cunha

机构 * Centro de Informática, Universidade Federal de Pernambuco, Brazil（巴西佩鲁巴伦斯联邦大学计算机中心） ； Center for Image Analysis, Beckman Institute, California Institute of Technology, USA（美国加利福尼亚理工学院图像分析中心） 纠错

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

Comments Submitted to IEEE ISBI 2026

Is Noise Conditioning Necessary for Denoising Generative Models?

Qiao Sun, Zhicheng Jiang, Hanhong Zhao, Kaiming He

机构 * MIT（麻省理工学院） 纠错

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

Comments Update ImageNet experiments (SiT with CFG). Update Appendix

Journal ref Proceedings of the 42nd International Conference on Machine Learning (ICML), 2025

Search by Return: Stochastic Resetting in Fluctuating Harmonic Potentials

Derek Frydel

专题命中 扩散模型 ：diffusion(abstract)

Multi-network Topology Underlying Individual Language Learning Success

Peilun Song, Shuguang Yang, Xiujuan Geng, Zhenzhong Gan, Suiping Wang, Gangyi Feng

专题命中 扩散模型 ：diffusion(abstract)

Inertial active particles in a Poiseuille flow: negative mobility and particle separation

Ankit Gupta, P. S. Burada

专题命中 扩散模型 ：diffusion(abstract)

Homogenisation of a Passive Scalar Transported by Locally Supported White Noise

Federico Butori, Avi Mayorcas, Silvia Morlacchi

专题命中 扩散模型 ：diffusion(abstract)

Comments 37 pgs; 7 figs; keywords and classifications added

CO Adsorption Sites on Interstellar Water Ices Explored with Machine Learning Potentials. Binding energy distributions and snowline

Giulia M. Bovolenta, Germán Molpeceres, Kenji Furuya, Johannes Kästner, Stefan Vogt-Geisse

专题命中 扩散模型 ：diffusion(abstract)

Comments 19 pages, 13 figures. Accepted for publication in Astronomy and Astrophysics (A&A)

Journal ref A&A 703, A172 (2025)

Sample Variance Denoising in Cylindrical 21-cm Power Spectra

Daniela Breitman, Andrei Mesinger, Steven G. Murray, Anshuman Acharya

专题命中 扩散模型 ：diffusion(abstract)

Comments 12 pages, 10 figures, submitted to A&A

Journal ref A&A 703, A130 (2025)

Wright--Fisher kernels: from linear to non-linear dynamics, ergodicity and McKean--Vlasov scaling limits

Fernando Cordero, Christian Jorquera, Héctor Olivero, Leonardo Videla

专题命中 扩散模型 ：diffusion(abstract)

Comments 41 pages, 3 figures

Instability of steady-state mixed-state symmetry-protected topological order to strong-to-weak spontaneous symmetry breaking

Jeet Shah, Christopher Fechisin, Yu-Xin Wang, Joseph T. Iosue, James D. Watson, Yan-Qi Wang, Brayden Ware, Alexey V. Gorshkov, Cheng-Ju Lin

专题命中 扩散模型 ：diffusion(abstract)

Comments 23+13 pages, 11+4 figures

Journal ref Quantum 9, 1912 (2025)

Skew-Normal Diffusions

Max-Olivier Hongler, Daniele Rinaldo

专题命中 扩散模型 ：diffusion(abstract)

Bridging the Gap Between Bayesian Deep Learning and Ensemble Weather Forecasts

Xinlei Xiong, Wenbo Hu, Shuxun Zhou, Kaifeng Bi, Lingxi Xie, Ying Liu, Richang Hong, Qi Tian

机构 * Hefei University of Technology（合肥工业大学） ； Huawei Inc.（华为公司） 纠错

专题命中 扩散模型 ：diffusion(abstract)

Collaborative QA using Interacting LLMs. Impact of Network Structure, Node Capability and Distributed Data

Adit Jain, Vikram Krishnamurthy, Yiming Zhang

机构 * Department of Electrical and Computer Engineering, Cornell University（电气与计算机工程系，康奈尔大学） 纠错

专题命中 扩散模型 ：diffusion(abstract)

On the Time Derivative of the KL Divergence for a Generalized Langevin Annealing Scheme

Andreas Habring

专题命中 扩散模型 ：diffusion(abstract)

Spatially Correlated Noise Induces Transitions from the Diffusive to Ballistic Regime in Fluids

Sijie Huang, Ayush Saurabh, Steve Presse

专题命中 扩散模型 ：diffusion(abstract)

Iris: Integrating Language into Diffusion-based Monocular Depth Estimation

Ziyao Zeng, Jingcheng Ni, Daniel Wang, Patrick Rim, Younjoon Chung, Fengyu Yang, Byung-Woo Hong, Alex Wong

机构 * Yale University（耶鲁大学） ； Brown University（布朗大学） ； Chung-Ang University（Chung-Ang 大学） 纠错

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

PFAvatar: Pose-Fusion 3D Personalized Avatar Reconstruction from Real-World Outfit-of-the-Day Photos

Dianbing Xi, Guoyuan An, Jingsen Zhu, Zhijian Liu, Yuan Liu, Ruiyuan Zhang, Jiayuan Lu, Yuchi Huo, Rui Wang

专题命中 可控生成 ：diffusion(abstract)；分类 cs.CV、cs.GR

Comments Accepted by AAAI 2026

Calibration of a Hybrid Local-Stochastic Volatility Stochastic Rates Model with a Control Variate Particle Method

Andrei Cozma, Matthieu Mariapragassam, Christoph Reisinger

专题命中 可控生成 ：diffusion(abstract)

Comments 45 pages

Measurement-Constrained Sampling for Text-Prompted Blind Face Restoration

Wenjie Li, Yulun Zhang, Guangwei Gao, Heng Guo, Zhanyu Ma

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Shanghai Jiao Tong University（上海交通大学） ； Nanjing University of Science and Technology（南京理工大学） 纠错

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

A Closed-Form Framework for Schrödinger Bridges Between Arbitrary Densities

Hanwen Huang

专题命中 图像修复 ：diffusion(abstract)；inpainting(abstract)

Comments 35 pages, 3 figures

UniVST: A Unified Framework for Training-free Localized Video Style Transfer

Quanjian Song, Mingbao Lin, Wengyi Zhan, Shuicheng Yan, Liujuan Cao, Rongrong Ji

机构 * Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, China（中国教育部多媒体可信感知与高效计算重点实验室，厦门大学，中国） ； Rakuten Asia Pte. Ltd. ； School of Computing, National University of Singapore（新加坡国立大学计算机学院） ； Institute of Artificial Intelligence, Xiamen University（厦门大学人工智能研究院） 纠错

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

Comments Accepted by TPAMI 2025; Project Page: https://quanjiansong.github.io/projects/UniVST

MedGEN-Bench: Contextually entangled benchmark for open-ended multimodal medical generation

Junjie Yang, Yuhao Yan, Gang Wu, Yuxuan Wang, Ruoyu Liang, Xinjie Jiang, Xiang Wan, Fenglei Fan, Yongquan Zhang, Feiwei Qin, Changmiao Wang

机构 * South China University of Technology（华南理工大学） ； Sun Yat-sen University（中山大学） ； Hangzhou Dianzi University（杭州电子科技大学） ； Zhejiang University of Finance & Economics（浙江财经大学） ； National University of Singapore（新加坡国立大学） ； Shenzhen Research Institute of Big Data（深圳大数据研究院） ； City University of Hong Kong（香港城市大学） 纠错

专题命中 图像生成评测 ：image generation(abstract)；image editing(abstract)；分类 cs.CV

Comments CVPR 2026 Under Review

Learning few-step posterior samplers by unfolding and distillation of diffusion models

Charlesquin Kemajou Mbakam, Jonathan Spence, Marcelo Pereyra

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

Comments 34 pages, 18 figures, 11 tables

Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantization

Weizhi Gao, Zhichao Hou, Junqi Yin, Feiyi Wang, Linyu Peng, Xiaorui Liu

机构 * Department of Computer Science, North Carolina State University（北卡罗来纳州立大学计算机科学系） ； National Center for Computational Science, Oak Ridge National Lab（橡树岭国家实验室计算科学中心） ； Department of Mechanical Engineering, Keio University（庆应大学机械工程系） 纠错

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

Comments 26 pages, accepted by ICML 2025

Journal ref Proceedings of the 42nd International Conference on Machine Learning, PMLR 267, 18337-18362, 2025

NERD: Network-Regularized Diffusion Sampling For 3D Computed Tomography

Shijun Liang, Ismail Alkhouri, Qing Qu, Rongrong Wang, Saiprasad Ravishankar

专题命中 效率与蒸馏 ：diffusion(title,abstract)

Journal ref CAMSAP2025