The first prior-fitted foundation model for survival analysis that enables zero-shot time-to-event predictions on tabular data.
April 1, 2026
Original Paper
Survival In-Context: Prior-fitted In-context Learning Tabular Foundation Model for Survival Analysis
arXiv · 2603.29475
The Takeaway
It extends the 'Prior-Fitted Networks' paradigm to medical survival analysis, removing the need for task-specific fine-tuning or hyperparameter search on small, censored datasets. This provides a plug-and-play foundation model for a domain traditionally dominated by handcrafted statistical models.
From the abstract
Survival analysis is crucial for many medical applications but remains challenging for modern machine learning due to limited data, censoring, and the heterogeneity of tabular covariates. While the prior-fitted paradigm, which relies on pretraining models on large collections of synthetic datasets, has recently facilitated tabular foundation models for classification and regression, its suitability for time-to-event modeling remains unclear. We propose a flexible survival data generation framewo