TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data
Abstract
Prior-Data Fitted networks (PFNs) have been very successful in tabular contexts, handling prediction tasks in context. However, they are designed for single-task inference, meaning that predicting several target values within a context requires repeated forward calls and precludes inter-task information sharing. We propose TabPFN-MT, which is trained on an expanded multi-target synthetic prior to capture inter-task dependencies in context. This model uses an expanded -encoder and a shared decoder head to enable multitask in-context learning and simultaneous inference. The model is uniquely specialized for small-to-medium datasets by relying on in-context learning rather than traditional gradient-based training. Within this regime (averaging fewer than 1,000 samples), extensive evaluations across 344 datasets demonstrate that TabPFN-MT establishes a new state-of-the-art for deep tabular multitask learning. Furthermore, despite the inherent compute asymmetry of joint optimization, our model remains highly competitive with the latest state-of-the-art single-task ensembles. Notably, on multitask datasets it achieves an overall Accuracy rank of 4.89, the highest average rank among all models tested. Crucially, TabPFN-MT delivers this highly competitive performance while reducing the inference cost for tasks from to forward passes, offering a massive computational efficiency improvement for multi-target tabular applications.
Cite
@article{arxiv.2605.20234,
title = {TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data},
author = {Cormac Cureton and Narges Armanfard},
journal= {arXiv preprint arXiv:2605.20234},
year = {2026}
}
Comments
24 pages, 7 figures