Can Graph Foundation Models Generalize Over Architecture?
University of Oxford（牛津大学）；AITHYRA
Benjamin Gutteridge, Michael Bronstein, Xiaowen Dong
备注：
9 pages main text + 18 pages references and appendix (27 pages total), 5 figures. Accepted to GRaM Workshop @ ICLR 2026: Workshop on Geometry-grounded Representation Learning and Generative Modeling (to appear in PMLR)
Graph foundation models (GFMs) have recently attracted interest due to the promise of graph neural network (GNN) architectures that generalize zero-shot across graphs of arbitrary scales, feature dimensions, and domains. While existing work has demonstrated this ability empirically across diverse real-world benchmarks, these tasks share a crucial hidden limitation: they admit a narrow set of effective GNN architectures. In particular, current domain-agnostic GFMs rely on fixed architectural backbones, implicitly assuming that a single message-passing regime suffices across tasks. In this paper, we argue that architecture adaptivity is a necessary requirement for true GFMs. We show that existing approaches are non-robust to task-dependent architectural attributes and, as a case study, use range as a minimal and measurable axis along which this limitation becomes explicit. With theoretical analysis and controlled synthetic experiments, we demonstrate that fixed-backbone GFMs provably under-reach on tasks whose architectural requirements differ from those seen at training time. To address this issue, we introduce a framework that adapts effective GNN architecture at inference time by discovering and mixing task-specific linear graph operators, enabling zero-shot generalization across tasks with heterogeneous architectural requirements, without retraining. We validate our approach on arbitrary-range synthetic tasks and a suite of real-world benchmarks, demonstrating improved performance and robustness over existing domain-agnostic GFMs.
KairosHope: A Next-Generation Time-Series Foundation Model for Specialized Classification via Dual-Memory Architecture
Department of Computer Science and Artificial Intelligence（计算机科学与人工智能系）；DiCITS, iMUDS, DaSCI（DiCITS、iMUDS、DaSCI）；University of Granada（格拉纳达大学）；Advanced Medical Imaging Group（先进医学成像组）；Instituto de Investigación Biosanitaria de Granada (ibs.Granada)（格拉纳达生物医学研究机构（ibs.Granada））；Department of Software Engineering（软件工程系）；Department of Rural Engineering（农村工程系）；University of Córdoba（科尔多瓦大学）
Time Series Foundation Models and Deep Learning Architectures for Earthquake Temporal and Spatial Nowcasting
University of Virginia（弗吉尼亚大学）；University of California, Davis（加州大学戴维斯分校）；Santa Fe Institute（圣达菲研究所）；Jet Propulsion Laboratory（喷气推进实验室）；California Institute of Technology（加州理工学院）；University of California, Irvine（加州大学欧文分校）
Hierarchical Federated Foundation Models over Wireless Networks for Multi-Modal Multi-Task Intelligence: Integration of Edge Learning with D2D/P2P-Enabled Fog Learning Architectures
BioArc: Discovering Optimal Neural Architectures for Biological Foundation Models
Department of Computer Science, Virginia Tech, Blacksburg, VA, USA（弗吉尼亚理工学院计算机科学系）；Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA（弗吉尼亚理工学院电气与计算机工程系）；Department of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA（卡内基梅隆大学计算机科学系）；Department of Biomedical Data Science, Stanford University, Stanford, CA, USA（斯坦福大学生物医学数据科学系）
SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Model
Department of Electronics, Information and Bioengineering, Politecnico di Milano（电子工程与信息生物工程系，米兰理工大学）；State Key Laboratory of Industrial Control Technology, Zhejiang University（工业控制技术国家重点实验室，浙江大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院）；Nell Hodgson Woodruff School of Nursing, Emory University（埃默里大学护理学院）
Channel Adaptation for EEG Foundation Models: A Systematic Benchmark Across Architectures, Tasks, and Training Regimes
Swartz Center for Computational Neuroscience, Institute for Neural Computation, University of California San Diego（斯瓦茨计算神经科学中心，神经计算研究所，加州大学圣地亚哥分校）；Yneuro；Centre de Recherche Cerveau et Cognition, CNRS, Université Paul Sabatier（脑与认知研究中心，法国国家科学研究中心，保罗·萨巴蒂埃大学）
SPUS: A Lightweight and Parameter-Efficient Foundation Model for PDEs
Computing and Artificial Intelligence Division (CAI)（计算与人工智能部门）；Space Remote Sensing and Data Science（空间遥感与数据科学）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）
Developing a Foundation of Vector Symbolic Architectures Using Category Theory
Cheriton School of Computer Science University of Waterloo（滑铁卢大学切尔顿计算机科学学院）；Centre for Theoretical Neuroscience Systems Design Engineering University of Waterloo（滑铁卢大学理论神经科学中心系统设计工程学院）；Department of Psychology University of Waterloo（滑铁卢大学心理学系）
本文首次将范畴论应用于向量符号架构，将向量推广为余预层，并把 VSA 操作形式化为外部张量积的右 Kan 扩展，通过示例验证了该形式化并为 VSA 新设计提供思路。
Towards Neural Scaling Laws for Time Series Foundation Models
Griffith University（格里菲斯大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；NVIDIA Research（英伟达研究院）；The University of Tokyo（东京大学）
Exhaustive Circuit Mapping of a Single-Cell Foundation Model Reveals Massive Redundancy, Heavy-Tailed Hub Architecture, and Layer-Dependent Differentiation Control
Department of Computer Science, University of Tübingen（图宾根大学计算机科学系）
TOLiD: Bridging the Architecture Gap in Vision Foundation Model to LiDAR Pretraining via Token Lifting for Distillation
SAIVT Group, School of Electrical Engineering and Robotics, Queensland University of Technology（澳大利亚昆士兰科技大学电气工程与机器人学院SAIVT组）；CSIRO Robotics, CSIRO（澳大利亚联邦科学与工业研究组织机器人部）
CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model
Saw Swee Hock School of Public Health, National University of Singapore（新加坡国立大学 Saw Swee Hock 公共卫生学院）；Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所）；Guangzhou Research Translation and Innovation Institute, National University of Singapore（新加坡国立大学广州研究翻译与创新研究所）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Beijing Key Laboratory of Brainnetome and Brain-Computer Interface, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所脑网络与脑机接口重点实验室）；Brainnetome Center, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所脑网络中心）
Neural Architectures for Amortized Bayesian Inference: Statistical Foundations and Empirical Assessments
Department of Mathematics and Statistics, Indian Institute of Technology Kanpur（数学与统计学系，印度理工学院坎浦尔分校）；Marshall School of Business, University of Southern California（马歇尔商学院，南加州大学）
The Platonic Universe: Do Foundation Models See the Same Sky?
Independent Researcher（独立研究者）；AstroAI；Harvard-Smithsonian CfA（哈佛-史密松天体物理中心）；University of Hertfordshire（赫特福德郡大学）；Washington University St. Louis（圣路易斯华盛顿大学）；Space Telescope Science Institute（空间望远镜科学研究所）；Johns Hopkins University（约翰霍普金斯大学）
