图像生成

SparseDiT: Token Sparsification for Efficient Diffusion Transformer

Shuning Chang, Pichao Wang, Jiasheng Tang, Fan Wang, Yi Yang

机构 * Zhejiang University（浙江大学） ； Damo Academy, Alibaba Group（阿里达摩院） ； Hupan Lab（虎斑实验室） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)；分类 cs.CV

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

Penalizing Boundary Activation for Object Completeness in Diffusion Models

Haoyang Xu, Tianhao Zhao, Sibei Yang, Yutian Lin

机构 * School of Computer Science, Wuhan University（武汉大学计算机学院） ； School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation

Lianwei Yang, Haokun Lin, Tianchen Zhao, Yichen Wu, Hongyu Zhu, Ruiqi Xie, Zhenan Sun, Yu Wang, Qingyi Gu

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； Department of Electronic Engineering, Tsinghua University（清华大学电子工程系） ； School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院） ； Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

Sherwin Bahmani, Tianchang Shen, Jiawei Ren, Jiahui Huang, Yifeng Jiang, Haithem Turki, Andrea Tagliasacchi, David B. Lindell, Zan Gojcic, Sanja Fidler, Huan Ling, Jun Gao, Xuanchi Ren

机构 * NVIDIA ； University of Toronto（多伦多大学） ； Vector Institute（向量研究所） ； Simon Fraser University（西蒙弗雷泽大学） 纠错

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

Comments Project Page: https://research.nvidia.com/labs/toronto-ai/lyra/

SpinMeRound: Consistent Multi-View Identity Generation Using Diffusion Models

Stathis Galanakis, Alexandros Lattas, Stylianos Moschoglou, Bernhard Kainz, Stefanos Zafeiriou

机构 * Imperial College London（伦敦帝国学院） ； FAU Erlangen–Nürnberg（埃森哲-纽伦堡大学） 纠错

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

LiDAR Point Cloud Image-based Generation Using Denoising Diffusion Probabilistic Models

Amirhesam Aghanouri, Cristina Olaverri-Monreal

机构 * Johannes Kepler University Linz（约翰·凯撒大学林茨） ； Department Intelligent Transport Systems（智能交通系统部门） 纠错

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

Source-Free Domain Adaptive Semantic Segmentation of Remote Sensing Images with Diffusion-Guided Label Enrichment

Wenjie Liu, Hongmin Liu, Lixin Zhang, Bin Fan

机构 * School of Intelligence Science and Technology, University of Science and Technology Beijing（智能科学与技术学院，科学技术大学） ； Institute of Artificial Intelligence, University of Science and Technology Beijing（人工智能研究院，科学技术大学） 纠错

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

StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models

Haoxin Yang, Bangzhen Liu, Xuemiao Xu, Cheng Xu, Yuyang Yu, Zikai Huang, Yi Wang, Shengfeng He

机构 * South China University of Technology（南方科技大学） ； Singapore Management University（新加坡国立管理学院） ； Dongguan University of Technology（东莞大学） 纠错

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

Comments Accepted by NeurIPS 2025

Diffusion-Based Action Recognition Generalizes to Untrained Domains

Rogerio Guimaraes, Frank Xiao, Pietro Perona, Markus Marks

机构 * California Institute of Technology（加州理工学院） 纠错

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

Comments Project page: https://www.vision.caltech.edu/actiondiff. Code: https://github.com/frankyaoxiao/ActionDiff

Latent Beam Diffusion Models for Generating Visual Sequences

Guilherme Fernandes, Vasco Ramos, Regev Cohen, Idan Szpektor, João Magalhães

机构 * NOVA LINCS, NOVA School of Science and Technology（NOVA LINCS、NOVA科学与技术学校） 纠错

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

HDM: Hybrid Diffusion Model for Unified Image Anomaly Detection

Zekang Weng, Jinjin Shi, Jinwei Wang, Zeming Han

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

Comments The paper is withdrawn owing to issues found in the experimental results

DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction

Bowen Song, Jason Hu, Zhaoxu Luo, Jeffrey A. Fessler, Liyue Shen

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

Journal ref Neural Information Processing Systems (NeurIPS), 2024

Learning Image Priors through Patch-based Diffusion Models for Solving Inverse Problems

Jason Hu, Bowen Song, Xiaojian Xu, Liyue Shen, Jeffrey A. Fessler

机构 * Department of Electrical and Computer Engineering University of Michigan（电气与计算机工程系 华盛顿大学） 纠错

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

Journal ref Neural Information Processing Systems (NeurIPS), 2024

A Gradient Flow Approach to Solving Inverse Problems with Latent Diffusion Models

Tim Y. J. Wang, O. Deniz Akyildiz

专题命中 扩散模型 ：diffusion(title,abstract)

Comments Accepted at the 2nd Workshop on Frontiers in Probabilistic Inference: Sampling Meets Learning, 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

Stability and Generalization of Adversarial Diffusion Training

Hesam Hosseini, Ying Cao, Ali H. Sayed

机构 * School of Engineering, École Polytechnique Fédérale de Lausanne（瑞士联邦理工学院工程学院） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)

High-order finite element methods for three-dimensional multicomponent convection-diffusion

Aaron Baier-Reinio, Patrick E. Farrell

专题命中 扩散模型 ：diffusion(title,abstract)

Direct Preference Optimization for Speech Autoregressive Diffusion Models

Zhijun Liu, Dongya Jia, Xiaoqiang Wang, Chenpeng Du, Shuai Wang, Zhuo Chen, Haizhou Li

专题命中 扩散模型 ：diffusion(title,abstract)

Query-Centric Diffusion Policy for Generalizable Robotic Assembly

Ziyi Xu, Haohong Lin, Shiqi Liu, Ding Zhao

机构 * Department of Mechanical Engineering, Carnegie Mellon University（机械工程系，卡内基梅隆大学） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)

Comments 8 pages, 7 figures

3D Flow Diffusion Policy: Visuomotor Policy Learning via Generating Flow in 3D Space

Sangjun Noh, Dongwoo Nam, Kangmin Kim, Geonhyup Lee, Yeonguk Yu, Raeyoung Kang, Kyoobin Lee

机构 * School of Integrated Technology (SIT), Gwangju Institute of Science and Technology (GIST)（整合技术学院（SIT）、全州科学技术学院（GIST）） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)

Comments 7 main scripts + 2 reference pages

SynSonic: Augmenting Sound Event Detection through Text-to-Audio Diffusion ControlNet and Effective Sample Filtering

Jiarui Hai, Mounya Elhilali

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)

DSFT: Inspiring Diffusion Large Language Models to Comprehend Mathematical and Logical Patterns

Ranfei Chen, Ming Chen

机构 * Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China（智能信息处理重点实验室，计算技术研究所，中国科学院，北京，中国） ； Computer Network Information Center, Chinese Academy of Sciences, Beijing, China（计算机网络信息中心，中国科学院，北京，中国） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)

AdaSTI: Conditional Diffusion Models with Adaptive Dependency Modeling for Spatio-Temporal Imputation

Yubo Yang, Yichen Zhu, Bo Jiang

专题命中 扩散模型 ：diffusion(title,abstract)

Comments 9 pages

The Feller diffusion conditioned on a single ancestral founder

Conrad J. Burden, Robert C. Griffiths

专题命中 扩散模型 ：diffusion(title,abstract)

Comments 45 pages, 7 figures. Minor typos corrected for the published version. The second order subscripts are difficult to read in the published version but easily legible in this version

Journal ref Theoretical Population Biology 166(2025)1-15

Structure-prior Informed Diffusion Model for Graph Source Localization with Limited Data

Hongyi Chen, Jingtao Ding, Xiaojun Liang, Yong Li, Xiao-Ping Zhang

机构 * Shenzhen Key Laboratory of Ubiquitous Data Enabling, Shenzhen International Graduate School Tsinghua University Shenzhen China（深圳 ubiquitous 数据赋能关键实验室，深圳国际研究生院，清华大学，深圳，中国） ； Department of Electronic Engineering Tsinghua University Beijing China（电子工程系，清华大学，北京，中国） ； Pengcheng Laboratory Shenzhen China（鹏城实验室，深圳，中国） ； Pengcheng Laboratory（鹏城实验室） ； Tsinghua University（清华大学） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)

Comments CIKM 2025

Stoichiometry preservation and generalization of Bilger mixture fraction for non-premixed combustion with differential molecular diffusion

Haifeng Wang, Tianfang Xie

专题命中 扩散模型 ：diffusion(title,abstract)

Comments There appears to be an error in the paper. Particularly, the Peters mixture fraction was incorrectly claimed to preserve stoichiometry. In fact, it does not preserve stoichiometry. Thus we request to withdraw this paper

First-principles study on Small Polaron and Li diffusion in layered LiCoO2

Seryung Ahn, Jiyeon Kim, Bongjae Kim, Sooran Kim

专题命中 扩散模型 ：diffusion(title,abstract)

Validation of a Reynolds-averaged numerical simulation environment to simulate high-pressure, auto-igniting hydrogen diffusion flames

N. Diepstraten, L. M. T. Somers, J. A. van Oijen

专题命中 扩散模型 ：diffusion(title)

Comments Submitted to Combustion and Flame

An h-space Based Adversarial Attack for Protection Against Few-shot Personalization

Xide Xu, Sandesh Kamath, Muhammad Atif Butt, Bogdan Raducanu

机构 * Computer Vision Center Universitat Autònoma de Barcelona（计算机视觉中心自治大学巴塞罗那） 纠错

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

Comments 32 pages, 15 figures. Accepted by ACM Multimedia 2025

FixingGS: Enhancing 3D Gaussian Splatting via Training-Free Score Distillation

Zhaorui Wang, Yi Gu, Deming Zhou, Renjing Xu

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港理工大学（广州）） 纠错

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

Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generation

Muhammad Adnan, Nithesh Kurella, Akhil Arunkumar, Prashant J. Nair

机构 * The University of British Columbia（不列颠哥伦比亚大学） ； d-Matrix 纠错

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

Comments Accepted at the 39th Conference on Neural Information Processing Systems (NeurIPS), 2025