Test-Time Compute for Tabular Foundation Models: Mechanisms, Gains, and Limits
Which forms of test-time compute improve the predictions of strong pretrained tabular foundation models (TFMs)?
ProofPaper ↗
Key points
- We systematically study this along three axes: adaptation, aggregation, and context construction.
- Our evaluation spans modern TFMs across the TabArena benchmark, supplemented by experiments on wide and large-scale tables from OpenML.
- For adaptation, we introduce DiagScale, a diagonal query-key similarity update.
- For context construction, attention-guided retrieval improves TabPFN-3's predictions on some large tables and supports source pools beyond the full context memory limit.
Sources (1)
- [1]Test-Time Compute for Tabular Foundation Models: Mechanisms, Gains, and LimitsarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 02:09 PM
Which forms of test-time compute improve the predictions of strong pretrained tabular foundation models (TFMs)?
We systematically study this along three axes: adaptation, aggregation, and context construction.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 8, 2026Understanding Jev, the new model everyone is talking about
- Oct 8, 2026SuperNav: An Agentic Navigation System for Any Task in Any Scene
- Oct 8, 2026VibeEdit: Image Editing with Canvas Instructions
- Oct 7, 2026One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO
- Oct 7, 2026Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning
- Oct 7, 2026Q-Learning with Scalar Adjoint Matching