Recent work has shown diffusion models are an effective approach to learning the multimodal distributions arising from demonstration data in behavior cloning. However, a drawback of this approach is the need to learn a denoising function, which is significantly more complex than learning an explicit policy. In this work, we propose Equivariant Diffusion Policy, a novel diffusion policy learning method that leverages domain symmetries to obtain better sample efficiency and generalization in the denoising function. We theoretically analyze the $\mathrm{SO}(2)$ symmetry of full 6-DoF control and characterize when a diffusion model is $\mathrm{SO}(2)$-equivariant. We furthermore evaluate the method empirically on a set of 12 simulation tasks in MimicGen, and show that it obtains a success rate that is, on average, 21.9% higher than the baseline Diffusion Policy. We also evaluate the method on a real-world system to show that effective policies can be learned with relatively few training samples, whereas the baseline Diffusion Policy cannot.
Frame-based Equivariant Diffusion Models for 3D Molecular Generation
University of Amsterdam(阿姆斯特丹大学);AMLab;AI4Science Lab(AI4Science实验室);Korteweg-de Vries Institute for Mathematics University of Amsterdam(Korteweg-de Vries数学研究所阿姆斯特丹大学)
Equivariant Diffusion for Crystal Structure Prediction
School of Computer Science;Engineering, Sun Yat-sen University, Guangzhou, China;National Supercomputer Center in Guangzhou, China;Dept. of Comp. Sci. \& Tech., Institute for AI, Tsinghua University, Beijing, China;Institute for AIR, Tsinghua University, Beijing, China;Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China;Beijing Key Laboratory of Big Data Management;Analysis Methods, Beijing, China
Loop-Diffusion: an equivariant diffusion model for designing and scoring protein loops
University of Washington(华盛顿大学);Paul G. Allen School of Computer Science and Engineering, University of Washington(华盛顿大学保罗·G·艾伦计算机科学与工程学院);Department of Applied Mathematics, University of Washington(华盛顿大学应用数学系);Fred Hutch Cancer Research Center(弗雷德·哈钦森癌症研究中心)
Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation
Shanghai Academy of Artificial Intelligence for Science, SAIS(上海人工智能科学研究院,SAIS);College of Chemistry and Chemical Engineering, Xiamen University(厦门大学化学与化工学院);Artificial Intelligence Innovation and Incubation (AI 3 ) Institute, Fudan University(复旦大学人工智能创新与孵化(AI 3)研究院)
D3MES: Diffusion Transformer with multihead equivariant self-attention for 3D molecule generation
School of Physics and Electronic Engineering, Jiangsu University(江苏大学物理与电子工程学院);Jiangsu Engineering Research Center on Quantum Perception and Intelligent Detection of Agricultural Information(江苏省农业信息量子感知与智能检测工程研究中心)
Crystal Structure Prediction by Joint Equivariant Diffusion
Tsinghua University(清华大学);Institute for AI, Tsinghua University(清华大学人工智能研究院);Institute for AIR, Tsinghua University(清华大学AIR研究院);Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);National Supercomputer Center in Guangzhou(广州国家超级计算中心);School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院);Stanford University(斯坦福大学)
Generalizable Equivariant Diffusion Models for Non-Abelian Lattice Gauge Theory
Centre for Quantum Fields and Gravity, Department of Physics, Swansea University(量子场与引力中心,物理系,萨瑟兰大学);Institute for Theoretical Physics, TU Wien(理论物理研究所,维也纳技术大学);RIKEN Center for Interdisciplinary Theoretical and Mathematical Sciences (iTHEMS)(理化学研究所跨学科理论和数学科学中心(iTHEMS));Institute for Physics of Intelligence, Graduate School of Science, The University of Tokyo(智能物理研究所,科学研究生院,东京大学);State Key Laboratory of Dark Matter Physics, Key Laboratory for Particle Astrophysics and Cosmology (MOE), Shanghai Key Laboratory for Particle Physics and Cosmology, Shanghai Jiao Tong University(暗物质物理国家重点实验室,粒子天体物理与宇宙学重点实验室(MOE),粒子物理与宇宙学上海重点实验室,上海交通大学);Southern Center for Nuclear-Science Theory (SCNT), Institute of Modern Physics, Chinese Academy of Sciences(南方核科学理论中心(SCNT),现代物理研究所,中国科学院)
Elign: Equivariant Diffusion Model Alignment from Foundational Machine Learning Force Fields
Department of Computer Science, Yale University, New Haven, USA(计算机科学系,耶鲁大学,新 Haven,USA);Program in Computational Biology and Biomedical Informatics, Yale University, New Haven, USA(计算生物学与生物医学信息学项目,耶鲁大学,新 Haven,USA);IQuestLab
Antibody Design and Optimization with Multi-scale Equivariant Graph Diffusion Models for Accurate Complex Antigen Binding
School of Computer Science, Wuhan University, Wuhan, China(武汉大学计算机学院);Department of Computing, Macquarie University, Sydney, Australia(麦考瑞大学计算机系);Wuhan University Shenzhen Research Institute, Shenzhen, China(武汉大学深圳研究院)
Structure-based Drug Design with Equivariant Diffusion Models
École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院);University of Cambridge(剑桥大学);Cornell University(康奈尔大学);Prescient Design, Genentech(普雷赛特设计公司,基因泰克公司);Chinese Academy of Mathematics and System Science(中国科学院数学与系统科学研究院);Heart and Lung Research Institute, University of Cambridge(剑桥大学心肺研究所);University of Rome “La Sapienza”(罗马大学);Microsoft Research AI4Science(微软研究院AI4Science);University of Amsterdam(阿姆斯特丹大学);University of Oxford(牛津大学);AITHYRA Institute(艾西拉研究所)