Drifting models train one-step generators by optimizing a kernel-induced mean-shift discrepancy between the data and model distributions, with Laplace kernels used by default in practice. At each point, this discrepancy compares the kernel-weighted displacement toward nearby data samples with the corresponding displacement toward nearby model samples, thereby defining a transport direction for generated samples. In this paper, we show that drifting is more closely connected to score-based generative modeling than it may first appear, establishing a precise link to the score-matching principle underlying diffusion models. For Gaussian kernels, the population mean-shift field exactly equals the difference between the scores (i.e., the gradient-log-densities) of the Gaussian-smoothed data and model distributions. This identity follows from Tweedie's formula, which links the score of a Gaussian-smoothed density to its conditional mean, and implies that Gaussian-kernel drifting is exactly a score-matching objective on smoothed distributions. More generally, we derive an exact decomposition for radial kernels in which mean shift equals a score-based field plus a residual term. For the practical Laplace kernel, we further show theoretically and empirically that this residual is negligible in high dimension, implying that the transport field used in practice is nearly score-based. Our results reveal a structural connection to diffusion models: both methods use score-mismatch transport directions, but drifting realizes the score nonparametrically through kernel-based estimates, whereas diffusion models learn it parametrically with neural networks.
Teacher-Feature Drifting: One-Step Diffusion Distillation with Pretrained Diffusion Representations
JD Explore Academy(京东探索研究院);Peking University(北京大学);Tsinghua University(清华大学);The Hong Kong University of Science and Technology(香港科技大学);Beijing Institute of Technology(北京理工大学)
Generative Drifting for Conditional Medical Image Generation
Department of Orthodontics and Orofacial Orthopedics, Friedrich-Alexander-University Erlangen-Nuremberg(口腔正畸与面部骨科系,弗里德里希-艾萨克-埃尔兰-纽伦堡大学);Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-University Erlangen-Nuremberg(生物医学工程人工智能系,弗里德里希-艾萨克-埃尔兰-纽伦堡大学);Pattern Recognition Lab, Friedrich-Alexander-University Erlangen-Nuremberg(模式识别实验室,弗里德里希-艾萨克-埃尔兰-纽伦堡大学);Department of Biomedical Engineering, Sun-Yat-sen University(生物医学工程系,孙中山大学)
ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation
School of Artificial Intelligence, Nanjing University of Information Science and Technology(南京信息工程大学人工智能学院);Department of Automation, Tsinghua University(清华大学自动化系);Lenovo(联想)
Eberhard Karls Universität Tübingen(图宾根大学);Max Planck Institute for Biogeochemistry(马克斯·普朗克生物地球化学研究所);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)
Inclusive Interactive Collisions for Multi-View Consistent Compositional 3D Generation
School of Computer Science and Technology, China University of Petroleum (East China)(中国石油大学(华东)计算机科学与技术学院);Artificial Intelligence Research Institute, Shenzhen University of Advanced Technology(深圳理工大学人工智能研究院);College of Computer Science, Northwest University(西北大学计算机科学学院)
Identity Preserving 3D Head Stylization with Multiview Score Distillation
Bilkent University(比尔肯大学);ETH Zurich(苏黎世联邦理工学院);Max Planck Institute(马克斯·普朗克研究所);INSAIT, Sofia University “St. Kliment Ohridski”(INSAIT,索菲亚大学“圣克莱门特·奥赫里茨基”)
AQuA -- Combining Experts' and Non-Experts' Views To Assess Deliberation Quality in Online Discussions Using LLMs
Heinrich Heine University Düsseldorf(杜塞尔多夫海因里希·海涅大学);Technical University Ilmenau(伊尔默瑙工业大学);Johannes Gutenberg University Mainz(美因茨约翰内斯·古腾堡大学);Technical University Dortmund(多特蒙德工业大学)
Clusterability-Based Assessment of Potentially Noisy Views for Multi-View Clustering
School of Software, Dalian University of Technology(大连理工大学软件学院);Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province(辽宁省 ubiquitous 网络与服务软件重点实验室)
A Hybrid CNN-VSSM model for Multi-View, Multi-Task Mammography Analysis: Robust Diagnosis with Attention-Based Fusion
Department of Mathematics and Statistics, Qatar University(数学与统计学系,卡塔尔大学);Department of Computer Science and Engineering, Qatar University(计算机科学与工程系,卡塔尔大学);Department of Electrical Engineering, Qatar University(电气工程系,卡塔尔大学);Graduate School of Information Science, University of Hyogo(信息科学研究生院,广岛大学);Advanced Medical Engineering Research Institute, University of Hyogo(先进医疗工程研究所,广岛大学)