AI 中文总结
本文研究表格基础模型的内存需求，采用模型压缩方法可实现最高7.6倍内存缩减，同时保持相近性能，降低近87%部署需求，为从业者高效部署这类模型提供见解。
AI 中文摘要
表格基础模型（如TabPFN）近期因在上下文表格机器学习任务上的性能远超经典基线而受到大量关注，但这类模型的实际部署考量较少被关注。本文研究了这类模型的内存需求，证明采用模型压缩方法可实现最高7.6倍的内存缩减，同时保持相近性能，将部署需求降低近87%，为从业者在实际场景中高效部署这类模型提供了见解。
英文摘要
Tabular Foundation Models, such as TabPFN, have received a large amount of recent attention due to their performance on in-context tabular machine learning tasks, which often exceeds classical baselines. However, practical deployment considerations of these models has received less attention. In this paper we investigate the memory requirements for these models. We demonstrate that employing model compression approaches can enable memory reductions of up to 7.6 with similar levels of performance, reducing deployment requirements by nearly 87%. Our work provides insight to practitioners seeking efficient deployment of these models in practical settings.
Comments12 pages, 3 figures Accepted at FMSD @ ICML 2026
Journal refFMSD @ ICML 2026
