Foundation models have established unified representations for natural language processing, yet this paradigm remains largely unexplored for tabular data. Existing methods face fundamental limitations: LLM-based approaches lack retrieval-compatible vector outputs, whereas text embedding models often fail to capture tabular structure and numerical semantics. To bridge this gap, we first introduce the Tabular Embedding Benchmark (TabBench), a comprehensive suite designed to evaluate the tabular understanding capability of embedding models. We then propose TabEmbed, the first generalist embedding model that unifies tabular classification and retrieval within a shared embedding space. By reformulating diverse tabular tasks as semantic matching problems, TabEmbed leverages large-scale contrastive learning with positive-aware hard negative mining to discern fine-grained structural and numerical nuances. Experimental results on TabBench demonstrate that TabEmbed significantly outperforms state-of-the-art text embedding models, establishing a new baseline for universal tabular representation learning. Code and datasets are publicly available at https://github.com/qiangminjie27/TabEmbed and https://huggingface.co/datasets/qiangminjie27/TabBench.

翻译：基础模型已为自然语言处理建立了统一的表示范式，然而这一范式在表格数据领域仍鲜有探索。现有方法存在根本性局限：基于大语言模型的方法缺乏检索兼容的向量输出，而文本嵌入模型则难以捕捉表格结构特征与数值语义。为弥合这一差距，我们首先提出表格嵌入基准测试（TabBench）——一个用于评估嵌入模型表格理解能力的综合性测试套件。继而提出TabEmbed——首个在共享嵌入空间内统一表格分类与检索任务的通用嵌入模型。通过将多样化表格任务重构为语义匹配问题，TabEmbed利用大规模对比学习与正样本感知难负样本挖掘技术，以辨别细粒度的结构与数值差异。在TabBench上的实验结果表明，TabEmbed显著优于现有最优文本嵌入模型，为通用表格表示学习建立了新基线。代码与数据集已在 https://github.com/qiangminjie27/TabEmbed 和 https://huggingface.co/datasets/qiangminjie27/TabBench 公开。