Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolate
灾难性组合生成:为什么普通扩散模型无法外推
Duncan Soiffer, Chandler Squires, Yuan Guan, Jason Hartford, Pradeep Ravikumar
机构
*
Machine Learning Department, Carnegie Mellon University(卡内基梅隆大学机器学习系)
;
Valence Labs
;
Department of Computer Science, University of Manchester(曼彻斯特大学计算机科学系)
机构
*
Institute for AI, University of Stuttgart(斯图加特大学人工智能研究所)
;
IMPRS-IS(国际马克斯·普朗克智能系统研究学院)
;
Institute of Theoretical Chemistry, University of Stuttgart(斯图加特大学理论化学研究所)
CoRDE: Concept-Prior Routed Diffusion Experts for Structural Generalization in Robot Manipulation
CoRDE:面向机器人操作结构泛化的概念先验路由扩散专家
Haidong Huang, Xixin Zhao, Yaohua Zhou, Jiayu Song, Jiayi Zhang, Jun Ma, Haiyue Zhu, Xiaocong Li
机构
*
College of Information Science and Technology, Eastern Institute of Technology, Ningbo(宁波东方理工大学(暂名)信息科学与技术学院)
;
Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin, Eastern Institute of Technology, Ningbo(浙江省工业智能与数字孪生重点实验室,宁波东方理工大学(暂名))
;
Department of Electrical and Computer Engineering, National University of Singapore(新加坡国立大学电气与计算机工程系)
;
Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)机器人与自主系统学域)
;
Faculty of Science and Engineering, University of Nottingham Ningbo China(宁波诺丁汉大学理工学院)
Diffusion Models Adapt to Low-Dimensional Structure Under Flexible Coefficient Choices
扩散模型在灵活系数选择下适应低维结构
Changxiao Cai, Yuchen Jiao, Gen Li
机构
*
Department of Industrial and Operations Engineering, University of Michigan(工业与运营工程系,密歇根大学)
;
Department of Statistics and Data Science, Chinese University of Hong Kong(统计与数据科学系,中国香港大学)