The ensemble average of physical properties of molecules is closely related to the distribution of molecular conformations, and sampling such distributions is a fundamental challenge in physics and chemistry. Traditional methods like molecular dynamics (MD) simulations and Markov chain Monte Carlo (MCMC) sampling are commonly used but can be time-consuming and costly. Recently, diffusion models have emerged as efficient alternatives by learning the distribution of training data. Obtaining an unbiased target distribution is still an expensive task, primarily because it requires satisfying ergodicity. To tackle these challenges, we propose Potential Score Matching (PSM), an approach that utilizes the potential energy gradient to guide generative models. PSM does not require exact energy functions and can debias sample distributions even when trained on limited and biased data. Our method outperforms existing state-of-the-art (SOTA) models on the Lennard-Jones (LJ) potential, a commonly used toy model. Furthermore, we extend the evaluation of PSM to high-dimensional problems using the MD17 and MD22 datasets. The results demonstrate that molecular distributions generated by PSM more closely approximate the Boltzmann distribution compared to traditional diffusion models.
Debiasing Guidance for Discrete Diffusion with Sequential Monte Carlo
University of Cambridge(剑桥大学);Technical University of Denmark(丹麦技术大学);Society of Fellows, Harvard University(哈佛大学 fellows 会);Institute for Artificial Intelligence(人工智能研究所);Massachusetts Institute of Technology(麻省理工学院)
Department of Artificial Intelligence, Westlake University, Hangzhou, China(人工智能系,西湖大学,杭州,中国);Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China(数学与系统科学研究院,中国科学院,北京,中国)
Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching
School of Statistics, East China Normal University(华东师范大学统计学院);Department of Statistics, University of California, Los Angeles(加州大学洛杉矶分校统计系);Department of Industrial and Systems Engineering, University of Minnesota(明尼苏达大学工业与系统工程系);School of Data Science, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)数据科学学院)
Gumbel-Softmax Flow Matching with Straight-Through Guidance for Controllable Biological Sequence Generation
Duke University(杜克大学);University of Pennsylvania(宾夕法尼亚大学);Duke-NUS Medical School(杜克-新加坡国立大学医学院);Mila, Quebec AI Institute(米拉魁北克人工智能研究所);Université de Montréal(蒙特利尔大学)
Value Gradient Guidance for Flow Matching Alignment
The Chinese University of Hong Kong (Shenzhen)(香港中文大学(深圳));University of Tübingen(图宾根大学);Microsoft Research(微软研究院);The Chinese University of Hong Kong(香港中文大学);Mila – Quebec AI Institute(魁北克AI研究所)
Path-Guided Flow Matching for Dataset Distillation
Department of Machine Learning, MBZUAI, Abu Dhabi, UAE(机器学习系,MBZUAI,阿布扎赫德,阿联酋);Department of Computer Vision, MBZUAI, Abu Dhabi, UAE(计算机视觉系,MBZUAI,阿布扎赫德,阿联酋)
Alignment of Diffusion Model and Flow Matching for Text-to-Image Generation
Department of Statistics, University of California, Los Angeles(加州大学洛杉矶分校统计学系);Department of Industrial and Systems Engineering, University of Minneasota(明尼苏达大学工业与系统工程系);School of Data Science, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)数据科学学院)
CREPE: Controlling Diffusion with Replica Exchange
University of Cambridge(剑桥大学);Technical University of Denmark(丹麦技术大学);University of Oxford(牛津大学);Cornell University(康奈尔大学);University of British Columbia(不列颠哥伦比亚大学);Xaira Therapeutics(Xaira制药公司)
Inference-Time Alignment for Diffusion Models via Variationally Stable Doob's Matching
Joint Laboratory of Data Science and Business Intelligence(数据科学与商业智能联合实验室);State Key Laboratory of Mathematical Sciences(数学科学国家重点实验室);Institut für Geometrie und Praktische Mathematik(几何与应用数学研究所);School of Artificial Intelligence(人工智能学院);School of Mathematics and Statistics(数学与统计学院)
Improving Discriminator Guidance in Diffusion Models
École Normale Supérieure Paris, PSL University(巴黎高等师范大学,巴黎大学);Mila, Quebec AI Institute, Université de Montréal(魁北克人工智能研究所,蒙特利尔大学);LAMSADE, CNRS, Université Paris-Dauphine-PSL(LAMSADE,国家科学研究中心,巴黎-dauphine-巴黎大学)
AdsorbFlow: energy-conditioned flow matching enables fast and realistic adsorbate placement
Beijing Key Laboratory of Artificial Intelligence for Advanced Chemical Engineering Materials, Department of Chemical Engineering, Tsinghua University(北京人工智能先进化工材料重点实验室,化学工程系,清华大学)
FlowQ: Energy-Guided Flow Policies for Offline Reinforcement Learning
Machine Learning Research Lab, Volkswagen Group(大众集团机器学习研究实验室);Technical University of Munich(慕尼黑技术大学);Foundation Robotics Labs, Munich(慕尼黑基础机器人实验室);Eötvös Loránd University(劳尔·艾尔多迪大学)