TabPFN-MT is a multitask in-context learner for tabular data that sets a new state-of-the-art on deep multitask learning for datasets under 1000 samples while reducing inference cost from O(T) to O(1) passes.
Interpretable
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 5years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Time series foundation models match the performance of specialized models for day-ahead load forecasting while providing explanations that match domain knowledge on weather and calendar effects.
TabPFN shows temporal specialization where one attention head dominates causal necessity at shifting peak layers depending on task complexity, while contrastive activation steering fails to transfer across samples due to context-dependent attention.
Pre-trained TabPFN acts as an effective training-free summary network for neural posterior estimation, matching or outperforming standard methods while preserving useful marginal and location information in the posterior.
TabPFN shows advantages over classical models in low-data and cross-country anemia prediction but performance differences are small and dominated by population variation rather than model architecture.
citing papers explorer
-
TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data
TabPFN-MT is a multitask in-context learner for tabular data that sets a new state-of-the-art on deep multitask learning for datasets under 1000 samples while reducing inference cost from O(T) to O(1) passes.
-
Explainable Load Forecasting with Covariate-Informed Time Series Foundation Models
Time series foundation models match the performance of specialized models for day-ahead load forecasting while providing explanations that match domain knowledge on weather and calendar effects.
-
Where Computation Lives Inside TabPFN: Causal Localisation of Attention Head Function
TabPFN shows temporal specialization where one attention head dominates causal necessity at shifting peak layers depending on task complexity, while contrastive activation steering fails to transfer across samples due to context-dependent attention.
-
Pre-trained Tabular Foundation Models as Versatile Summary Networks for Neural Posterior Estimation
Pre-trained TabPFN acts as an effective training-free summary network for neural posterior estimation, matching or outperforming standard methods while preserving useful marginal and location information in the posterior.
-
Few-shot Cross-country Generalization of Tabular Machine Learning and Foundation Models for Childhood Anemia Prediction under Distribution Shift
TabPFN shows advantages over classical models in low-data and cross-country anemia prediction but performance differences are small and dominated by population variation rather than model architecture.