We propose a new class of waveform foundation models that departs from conventional sequence based representations by modeling physiological time series as realizations of latent event processes. Rather than treating signals as collections of local tokens or patches, our approach assumes that clinically meaningful structure arises from temporally extended, interacting events whose boundaries and dynamics are not directly observed. To capture this structure, we introduce a self supervised learning framework that enforces consistency across stochastic segmentations and time frequency projections of the same waveform, encouraging representations that are invariant to signal level perturbations while preserving event level organization. The resulting model combines a segmentation aware encoder with a latent interaction operator that captures dependencies among inferred events, and naturally extends to multimodal settings by aligning modalities through shared event representations. Across a range of physiological benchmarks, including arrhythmia classification, hemodynamic prediction, and waveform retrieval, the proposed method improves performance, robustness, and label efficiency relative to strong sequence based baselines. These results suggest that shifting from signal centric to event centric representations provides a more appropriate inductive bias for modeling physiological dynamics and offers a complementary path to scaling foundation models in healthcare.
Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models
Department of Computing Science, University of Alberta, Canada(阿尔伯塔大学计算机科学系);Alberta Machine Intelligence Institute (Amii)(阿尔伯塔机器智能研究所);Canada CIFAR AI Chair(加拿大CIFAR人工智能 chair);The University of Texas at Austin(德克萨斯大学奥斯汀分校);University of Massachusetts Amherst(马萨诸塞大学阿姆赫斯特分校)
TabFORGE: A Tabular Foundation Model for Generative Modelling
Department of Computer Science and Technology, University of Cambridge, UK(计算机科学与技术系,剑桥大学,英国);SAP SE;Télécom Paris, Institut Polytechnique de Paris, France(巴黎telecom,巴黎理工 institute,法国)
EIDOS: Latent-Space Predictive Learning for Time Series Foundation Models
Nankai University(南开大学);Eindhoven University of Technology(埃因霍温理工大学);Yunnan University(云南大学);University of New South Wales(新南威尔士大学);Griffith University(格里菲斯大学)
University of Basel(巴塞尔大学);Université Grenoble Alpes(格勒诺布尔阿尔卑斯大学);Université Savoie Mont Blanc(萨瓦勃朗峰大学);CNRS(法国国家科学研究中心);Université Gustave Eiffel(埃菲尔大学);Sapienza University of Rome(罗马大学);Pennsylvania State University(宾夕法尼亚州立大学);Rice University(莱斯大学)
VAMP-Diff: VampPrior Latent Diffusion for Photoplethysmography Modeling
Department of Electrical and Computer Engineering(电气与计算机工程系);Clarkson University(克林顿大学);Department of Computer Science(计算机科学系);Worcester Polytechnic Institute(沃思格理工学院)
Continual Learning with Foundation Models: An Empirical Study of Latent Replay
ServiceNow(ServiceNow公司);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);Heuritech(Heuritech公司);HEC Montréal(蒙特利尔高等商学院);Sorbonne University(索邦大学);Canada CIFAR AI Chair(加拿大CIFAR人工智能讲席)
Decoding Latent Spaces: Assessing the Interpretability of Time Series Foundation Models for Visual Analytics
Computer Systems Engineering Dpt., Universidad Politécnica de Madrid, Madrid (Spain)(马德里理工大学计算机系统工程系);Department of Computer Science and Engineering, Seoul National University of Science and Technology, Seoul (Korea)(首尔科学技术大学计算机科学与工程系)
本研究评估了时间序列基础模型 MOMENT 在可视化分析任务中潜在空间的解释性,发现微调虽降低了损失但嵌入空间可解释性改善有限,指出基础模型仍需方法改进但显著提升了交互分析效率。
scDD: Latent Codes Based scRNA-seq Dataset Distillation with Foundation Model Knowledge
National Institute of Health Data Science, Peking University(北京大学健康数据科学国家研究院);Institute of Medical Technology, Peking University Health Science Center(北京大学医学部医学技术研究院);State Key Laboratory of General Artificial Intelligence, Peking University(北京大学通用人工智能国家重点实验室);AI Research Institute, China Mobile Communications Corporation(中国移动通信集团人工智能研究院);Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机技术研究院)
LUCoS: Latent Unsupervised Context Selection for Tabular Foundation Models
Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI)(安达卢西亚数据科学与计算智能研究 institute);Department of Computer Science and Artificial Intelligence (DECSAI)(计算机科学与人工智能系);Research Center in Information and Communication Technologies (CITIC)(信息与通信技术研究中心);Instituto de Investigación Biosanitaria Ibs.GRANADA, University of Granada, Granada, 18071, Spain(格拉纳达大学生物医学研究所)
FLAG: Foundation model representation with Latent diffusion Alignment via Graph for spatial gene expression prediction
Shanghai Academy of Artificial Intelligence for Science, Shanghai, China.(上海人工智能科学研究院);School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China.(上海交通大学生物医学工程学院);Incubation Institute, Fudan University, Shanghai, China.(复旦大学孵化院)
Probabilistic Geometric Alignment via Bayesian Latent Transport for Domain-Adaptive Foundation Models
School of Information, Computer;Communication Technology Sirindhorn International Institute of Technology, Thammasat University Pathumthani, Thailand 0009-0006-4313-7359;epartment of Architecture, Faculty of Architecture Khon Kaen University Khon Kaen, Thailand
Discrete Prototypical Memories for Federated Time Series Foundation Models
Australian Artificial Intelligence Institute, University of Technology Sydney(澳大利亚人工智能研究所,悉尼科技大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Shenzhen University(深圳大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Sichuan University(四川大学)
Foundation Model for Cardiac Time Series via Masked Latent Attention
Department of Computer Science, ETH Zurich, Switzerland(苏黎世联邦理工学院计算机科学系,瑞士);Department of Biomedical Engineering, University of Basel, Switzerland(巴塞尔大学生物医学工程系,瑞士)
Distilling latent electrostatics from foundation machine learning interatomic potentials
Department of Chemistry, UC Berkeley(加州大学伯克利分校化学系);Bakar Institute of Digital Materials for the Planet, UC Berkeley(伯克利大学数字材料研究所);Chemical Sciences Division, Lawrence Berkeley National Laboratory(伯克利国家实验室化学科学部)
DeepJEB++: Foundation Model-Driven Large-Scale 3D Engineering Dataset via 2D Latent Space Augmentation
Cho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology(韩国科学技术院赵春植移动研究生院);Department of Mechanical Engineering, Hanyang University(汉阳大学机械工程系);Narnia Labs(纳尼亚实验室)
CTSyn: A Foundation Model for Cross Tabular Data Generation
Department of Statistics and Data Science, University of California Los Angeles(统计与数据科学系,加州大学洛杉矶分校);Department of Computer Science, University of California Los Angeles(计算机科学系,加州大学洛杉矶分校)
LatentVerse: A Framework for Understanding Shared and Modality-Specific Information in Multimodal Latent Representations
Broad Institute of MIT and Harvard(麻省理工学院和哈佛大学布罗德研究所);Massachusetts Institute of Technology(麻省理工学院);The Schmidt Center, Broad Institute of MIT and Harvard(麻省理工学院和哈佛大学布罗德研究所施密特中心)
VFM-VAE: Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Models
State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University(人机混合增强智能国家重点实验室,人工智能与机器人研究院,西安交通大学);Microsoft Research Asia(微软亚洲研究院)
Using machine learning to parametrize postmerger signals from binary neutron stars
University of Waterloo(滑铁卢大学);Perimeter Institute for Theoretical Physics(圆周理论物理研究所);Max Planck Institute for Gravitational Physics (Albert Einstein Institute)(马克斯·普朗克引力物理研究所(阿尔伯特·爱因斯坦研究所));University of Guelph(圭尔夫大学)
Machine-learned particle flow as a foundation model for collider physics
University of California San Diego(加州大学圣地亚哥分校);National Institute of Chemical Physics and Biophysics(化学物理与生物物理国家研究所);SLAC National Accelerator Laboratory(斯坦福线性加速器中心国家加速器实验室)