Adapting Linear-Time Architectures for Tabular In-Context Learning
arXiv:2609.36337v1 Announce Type: cross Abstract: Tabular foundation models achieve strong performance by conditioning on labelled examples in context, but softmax attention limits their use on large datasets. Existing linear-time alternatives, however, are mostly causal, and their potential for ta…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-09-30 04:00 · arXiv stat.ML
Adapting Linear-Time Architectures for Tabular In-Context Learning