TabPFN-3 model boosts tabular data prediction and speed

A new technical report introduces TabPFN-3, an advanced foundation model for tabular data that significantly enhances performance and speed. This model scales to datasets with up to 1 million training rows and reduces training and inference times, outperforming existing models on benchmarks like TabArena. TabPFN-3 also extends its capabilities to time series, relational, and tabular-text data, setting new state-of-the-art results. AI

影响 Sets new SOTA on tabular benchmarks and accelerates inference, potentially impacting enterprise adoption for tabular data prediction.

排序理由 Publication of a technical report detailing a new model with benchmark results. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv stat.ML 阅读 →

• AutoGluon 1.5
• fev-bench
• RelBenchV1
• TabPFN
• TabPFN-2.5
• TabPFN-3
• TabPFN-3-Plus
• TabPFN-TS-3
• TabArena
• TabSTAR

• 模型发布
• 论文
• 产品

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →