aiqbench analysis
This research proposes a training-free method that leverages Tabular Foundation Models to address right-censoring in survival analysis, achieving performance competitive with traditional parametric models like Cox regression. By combining a single-parameter Accelerated Failure Time construction with a non-parametric in-context estimator, the approach offers a practical solution for time-to-event prediction without extensive dataset-specific fitting. The work highlights a promising direction for applying foundation models to complex statistical tasks where data is partially observed.
Staying Alive: Uncensored Survival Analysis with Tabular Foundation Models
arXiv:2606.03689v1 Announce Type: cross Abstract: Survival Analysis (SA) is a statistical framework that models the time span until some event of interest occurs. Widely used in several domains, including healthcare and churn prediction, a central challenge in its applicability stems from the time of the event being partially observed or \emph{right-censoring}. Tabular Foundation Models (TFM) have attracted significant interest in recent years due to their ability to perform prediction tasks in a single forward pass, requiring no dataset-specific parameter fitting. Despite their success, their application to prediction tasks on time-to-event data remains difficult due to right censoring. In this work, we present a training-free method to survival regression by leveraging TFMs to both predict the time of the event and iteratively impute right-censored data. Our method uses a TFM to construct an Accelerated Failure Time (AFT) model requiring no training beyond fitting a single scalar parameter. Subsequently, by building on the Buckley-James estimator, we introduce a non-parametric in-context estimator for right-censored data. Our experiments on standard survival analysis benchmarks show that our method is competitive with several parametric and semi-parametric survival regression models that require training, including Cox regression and parametric AFT models.
Abstract:Survival Analysis (SA) is a statistical framework that models the time span until some event of interest occurs. Widely used in several domains, including healthcare and churn prediction, a central challenge in its applicability stems from the time of the event being partially observed or \emph{right-censoring}. Tabular Foundation Models (TFM) have attracted significant interest in recent years due to their ability to perform prediction tasks in a single forward pass, requiring no dataset-specific parameter fitting. Despite their success, their application to prediction tasks on time-to-event data remains difficult due to right censoring. In this work, we present a training-free method to survival regression by leveraging TFMs to both predict the time of the event and iteratively impute right-censored data. Our method uses a TFM to construct an Accelerated Failure Time (AFT) model requiring no training beyond fitting a single scalar parameter. Subsequently, by building on the Buckley-James estimator, we introduce a non-parametric in-context estimator for right-censored data. Our experiments on standard survival analysis benchmarks show that our method is competitive with several parametric and semi-parametric survival regression models that require training, including Cox regression and parametric AFT models.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2606.03689 [cs.LG]
(or arXiv:2606.03689v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.03689 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 285 words
Related coverage
SurvICL: a Foundation Model for in-context Survival Analysis
arXiv · Oct 16, 2026
Lattice-Based Cryptography Explained
Quantum Zeitgeist · Aug 15, 2026
Tabular Foundation Models for Clinical Survival Analysis via Survival-Aware Adaptation
arXiv · Jun 12, 2026
Tabular Foundation Models Can Do Survival Analysis
arXiv · Jul 21, 2026