# Tydra: An Efficient Hybrid Model for Tabular Data

> Source: <https://www.machinebrief.com/news/tydra-an-efficient-hybrid-model-for-tabular-data-pip1>
> Published: 2026-08-24 04:00:00+00:00

arXiv:2608.21199v1 Announce Type: new
Abstract: Transformer-based tabular foundation models such as TabPFN achieve strong predictive performance but incur quadratic computational cost with context length. On the other hand, subquadratic SSM-based alternatives such as Hydra trade away accuracy for efficiency. To balance both, we introduce Tydra, a hybrid Transformer-State Space Model (SSM) architecture for tabular in-context learning that interleaves attention and SSM layers. Across 30 OpenML datasets, Tydra reduces inference time by 30% relative to TabPFN while retaining much of its predictive performance. Tydra also outperforms an approximately ten-times-larger Hydra model while providing faster inference. The results indicate that hybrid architectures are a promising direction for tabular foundation models.