Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data
Kai Helli, David Schnurr, Noah Hollmann, Samuel Müller, Frank Hutter
–Neural Information Processing Systems
Until now, no tabular method has consistently outperformed classical supervised learning, which ignores these shifts.
Neural Information Processing Systems
Feb-17-2026, 13:58:55 GMT
- Country:
- South America > Brazil
- Oceania > Australia
- New South Wales (0.04)
- North America > United States
- Minnesota > Olmsted County (0.04)
- Maryland (0.04)
- Iowa > Story County
- Ames (0.04)
- Europe
- France (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Switzerland > Zürich
- Zürich (0.04)
- Middle East > Republic of Türkiye
- Istanbul Province > Istanbul (0.04)
- Germany
- Bavaria > Upper Bavaria
- Munich (0.04)
- Baden-Württemberg
- Tübingen Region > Tübingen (0.04)
- Freiburg (0.04)
- Bavaria > Upper Bavaria
- Asia
- Singapore (0.04)
- India > Andhra Pradesh (0.04)
- Bangladesh (0.04)
- Middle East > Republic of Türkiye
- Istanbul Province > Istanbul (0.04)
- Genre:
- Research Report > New Finding (1.00)
- Industry:
- Banking & Finance (0.92)
- Transportation (0.92)
- Health & Medicine > Therapeutic Area
- Cardiology/Vascular Diseases (0.93)
- Endocrinology (0.68)