Prior-Data Fitted Networks (PFNs) perform approximate Bayesian inference in a single forward pass, and tabular foundation models (TFMs) built on them are now widely used. To understand what networks infer internally, recent mechanistic studies of TFMs locate where predictions form, but treat these models as tabular predictors rather than as PFNs. It therefore remains unknown whether PFNs represent the spectral content of their context, the quantity that specifies a stationary kernel, and whether this content can be read out as an explicit kernel. We answer both questions. First, across seven PFNs, including four pretrained TFMs and a model trained only on a decision-tree prior, a linear probe on the residual stream recovers the frequency of the context with $R^2 \geq 0.95$. This structure is led by a single principal direction. Second, activation and subspace patching show that the network uses the structure through a low-dimensional subspace, where a few spectral directions move predictions far more than random ones. This holds even for the decision-tree model, so a spectral training prior is not required. On real datasets with up to 499 features, 64 of the 192 directions of TabPFN, chosen without labels, carry 85 to 95\% of the causal effect of the context in all but one pair. Third, we introduce a Filter Bank Decoder that turns frozen PFN representations into an explicit stationary kernel through Bochner's theorem. Without any test-time optimization, the decoded kernel supports Gaussian process regression competitive with deep kernel learning and random Fourier features at about $200\times$ lower cost. PFN latents therefore hold spectral structure that is causally used and recoverable as a portable kernel.
University of Dublin, Trinity College(都柏林大学,三一学院);IBM;Gatsby Computational Neuroscience Unit, University College London(大学学院伦敦的加布里埃尔计算神经科学单位);Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI), Saarbrücken, Germany(德国萨尔布吕肯德意志人工智能研究中心(DFKI));Department of Philosophy, University of Bergen(卑尔根大学哲学系)
Survival In-Context: Amortized Bayesian Survival Analysis via Prior-Fitted Networks
Institute of Diagnostic and Interventional Radiology, Technical University of Munich, Germany(慕尼黑技术大学诊断与介入放射学研究所,德国);Chair for AI in Healthcare and Medicine, Technical University of Munich, Germany(慕尼黑技术大学医疗人工智能与医学研究所,德国);Hasso Plattner Institute for Digital Engineering, University of Potsdam, Germany(波茨坦大学数字工程哈索普兰特纳研究所,德国);University Hospital Hamburg-Eppendorf, Germany(汉堡-埃彭多夫大学医院,德国);Department of Computing, Imperial College London, UK(伦敦帝国理工学院计算系,英国);Munich Center for Machine Learning (MCML), Germany(慕尼黑机器学习中心(MCML),德国)
Department of Computer Science(计算机科学系);University of Technology Nuremberg(纽伦堡技术大学);Albert Ludwig University of Freiburg(弗赖堡阿尔伯特-路易斯大学);University of Elbasan(埃尔巴沙大学)
Prior-Fitted Functional Flow: In-Context Generative Models for Pharmacokinetics
University of Potsdam(波恩大学);Technical University Berlin(柏林技术大学);Freie Universität Berlin(柏林自由大学);University of Bonn(波恩大学);NHETC, Rutgers University(Rutgers大学国家健康教育与培训中心)
State-Space Models for Tabular Prior-Data Fitted Networks
L3S Research Center, Leibniz University Hannover, Hannover, Germany(L3S研究所以及汉诺威莱布尼茨大学);University of Applied Sciences Rosenheim, Rosenheim, Germany(罗斯海姆应用科学大学);Technical University of Munich, Munich, Germany(慕尼黑技术大学)
Prior-Fitted Networks Scale to Larger Datasets When Treated as Weak Learners
School of Computer Science, Fudan University(复旦大学计算机科学学院);Institute of Modern Languages and Linguistics, Fudan University(复旦大学现代语言与语言学研究所);Amazon(亚马逊公司)
Modelling of physical systems with a Hopf bifurcation using mechanistic models and machine learning
University of Bristol(布里斯托大学);Imperial College London(伦敦帝国学院)
我们提出了一种新的混合建模方法,结合了机械模型与机器学习模型来预测具有Hopf分岔的物理系统的极限环振荡。机械模型是一个常微分方程规范形式的模型捕捉系统的分岔结构。然后使用机器学习技术基于实验数据识别从该模型到实验观察的数据驱动映射。该方法首先在Van der Pol振子和三自由度气动弹性模型上进行了数值验证。然后,它被应用到模型的物理气动弹性结构的行为,表现出极限环振荡在风洞试验。该方法被证明是一般的,数据高效,并提供良好的精度,没有任何先验知识的系统以外的分歧结构。
Prior-Fitted and Frozen Scorers for Multimodal Contrastive Learning
Berlin Institute of Health(柏林卫生研究所);Charité - Universitätsmedizin Berlin(柏林夏里特医学院);Freie Universität Berlin(柏林自由大学);Intelligent Medicine Institute(智能医学研究所);Fudan University(复旦大学)