Get Started
Home
Topics
Search
Library
Research questionHow should tabular foundation models be adapted for censored time-to-event prediction under competing risks?Censoring hides some event times, while competing events change the risk structure that ordinary tabular prediction does not represent. The appropriate adaptation may also depend on the available data regime.
AI
Machine Learning
Research Paper
Statistical Machine Learning
Latest papersRecent research connected to this question, newest first.Adaptation Interfaces for In-Context Tabular Foundation Models in Time-to-Event PredictionThe study evaluates frozen tabular foundation model backbones with temporal zero-shot reformulation, classification fine-tuning, CoxPH, DeepHit, and survival-head adaptations on 74 single-risk and 4 competing-risk datasets. Results compare performance across dataset sizes and include time-dependent Concordance Index and Integrated Brier Score evidence.research paper · Sep 4, 2026
Related questions
How can general-purpose tabular predictors balance adaptation-free accuracy with computational cost?How should model architecture and size scale with data for noisy tabular ratemaking?How can wearable foundation models organize representations for targeted longitudinal women’s-health prediction?How can demographic information improve clinical tabular prediction across diseases and populations without complicating deployment?