# SurvPFN: Towards Foundation Models for Survival Predictions

Source: [SurvPFN: Towards Foundation Models for Survival Predictions](<https://www.sota2.com/research/paper/6a2106fcc10484bac23f071c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-30T05:00:05.200Z

Authors: Samuel B\\"ohm, Lennart Purucker, Frank Hutter, Pascal Schlosser (1,4,5) \_\_INSTITUTION\_4\_\_ Institute of Epidemiology, Prevention, Medical Center - University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany, (2) Department of Computer Science, University of Freiburg, Freiburg, Germany, (3) PriorLabs, Freiburg, Germany, (4) Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland, US, (5) CIBSS - Centre for Integrative Biological Signalling Studies, University of Freiburg, Freiburg, Germany)

Published: 2026-06-03T07:52:45.000Z

## Abstract

Tabular foundation models (TFMs) have made rapid progress in standard classification and regression, but time-to-event survival prediction tasks have remained largely untouched. Unlike in standard regression tasks, survival prediction models must account for censored data. Standard TFMs cannot handle natively censored data, leading to biased and inaccurate predictions, making them unsuitable for real-world applications. To overcome this fundamental limitation, we propose \\texttt{SurvPFN}, a prior-data fitted network (PFN), for survival prediction tasks. We pretrain \\texttt{SurvPFN} on millions of synthetic survival prediction tasks to learn survival via distributional regression that accounts for censored data. \\texttt{SurvPFN} works by (1) generating data with Weibull event times and a non-informative censoring mechanism; (2) integrating a censored event indicator; and (3) minimizing a censored negative log-likelihood. On SurvSet, a collection of real-world survival tasks, \\texttt{SurvPFN} is highly competitive with classical and deep survival baselines without per-dataset fitting, a survival-specific architecture, or feature engineering. We show that survival can be treated as a continuous-time distributional regression problem with censored loss, unlocking the power of PFNs for time-to-event predictions.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Survival Prediction on SurvSet 22 datasets average across all](<https://www.sota2.com/research/sota/survival-prediction-on-survset-22-datasets-average-across-all.md>): Survival Prediction; SurvSet 22 datasets average across all; C-Index: 0.777.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.04564>)

[PDF](<https://arxiv.org/pdf/2606.04564.pdf>)