SOMTab: Set-Order Mamba for Efficient Tabular In-Context Learning

• URL: http://arxiv.org/abs/2608.27882v1
• Date: Fri, 28 Aug 2026 03:43:08 GMT
• Title: SOMTab: Set-Order Mamba for Efficient Tabular In-Context Learning
• Abstract summary: We introduce SOMTab, a Set-Order Mamba architecture for efficient in-context learning.<n>For row and column representations, it maps unordered table tokens into stable latent slots and applies Mamba-based state-space mixing.<n>For final prediction, it retains attention-based in-context learning to preserve query-conditioned retrieval from labeled context examples.
• Score: 30.163512246197843
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Tabular foundation models based on in-context learning have recently emerged as strong alternatives to task-specific model fitting. However, the current performance frontier remains dominated by attention-heavy architectures, where attention is used throughout the modeling pipeline. This raises a natural question: is attention necessary at every stage of tabular in-context learning? We introduce SOMTab, a Set-Order Mamba architecture for efficient tabular in-context learning. SOMTab separates representation construction from query-conditioned retrieval. For row and column representations, it maps unordered table tokens into stable latent slots and applies Mamba-based state-space mixing to construct compact representations. For final prediction, it retains attention-based in-context learning to preserve query-conditioned retrieval from labeled context examples. We further introduce DCH-TailMix, a synthetic prior that combines degree-corrected graph heterogeneity with mixed heavy-tailed regimes to diversify synthetic dependency structures. Across tabular benchmarks, SOMTab approaches the performance of strong Transformer-based tabular foundation models while achieving faster inference and lower GPU memory usage, yielding a favorable efficiency--accuracy trade-off.

Related papers

• TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention [47.480923979431886]
  Tabular foundation models perform prediction via in-context learning, inferring test labels directly from labeled training examples.<n>Recent models often improve accuracy with increasingly complex architectures, incurring higher inference cost and limiting practical deployment.<n>We show that a lightweight row-wise attention-only backbone can remain highly competitive with two simple enhancements.
  arXiv  Detail & Related papers  (2026-06-05T14:55:30Z)
• TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding [35.46103363192022]
  We introduce the Tabular Embedding Benchmark (TabBench) to evaluate the capability of embedding models.<n>We then propose TabEmbed, the first generalist embedding model that unifies tabular classification and retrieval within a shared embedding space.<n> Experimental results on TabBench demonstrate that TabEmbed significantly outperforms state-of-the-art text embedding models.
  arXiv  Detail & Related papers  (2026-05-06T14:22:34Z)
• RDBLearn: Simple In-Context Prediction Over Relational Databases [21.996337463952255]
  We show that a simple recipe can be extended to relational prediction with a simple recipe.<n>We package this approach in textitRDBLearn, an easy-to-use toolkit with a scikit-learn-style estimator interface.<n>Across a broad collection of RelBench and 4DBInfer datasets, RDBLearn is the best-performing foundation model approach we evaluate.
  arXiv  Detail & Related papers  (2026-02-14T09:24:04Z)
• Comparing Task-Agnostic Embedding Models for Tabular Data [1.6479389738270018]
  This work specifically focuses on representation learning, i.e., on transferable, task-agnostic embeddings.<n>Tableizer features achieve comparable or superior performance while being up to three orders of magnitude faster than recent foundation models.
  arXiv  Detail & Related papers  (2025-11-18T09:10:40Z)
• Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models [85.64873567417396]
  We introduce Mitra, a TFM trained on a curated mixture of synthetic priors selected for their diversity, distinctiveness, and performance on real-world data.<n>Mitra consistently outperforms state-of-the-art TFMs, such as TabPFNv2 and TabICL, across both classification and regression benchmarks.
  arXiv  Detail & Related papers  (2025-10-24T07:15:06Z)
• Multimodal Tabular Reasoning with Privileged Structured Information [67.40011423365712]
  We introduce TabUlar Reasoning with Bridged infOrmation (sc Turbo)<n>sc Turbo benefits from a structure-aware reasoning trace generator based on DeepSeek-R1.<n>sc Turbo achieves state-of-the-art performance ($+7.2%$ vs. previous SOTA) across multiple datasets.
  arXiv  Detail & Related papers  (2025-06-04T15:46:30Z)
• MambaTab: A Plug-and-Play Model for Learning Tabular Data [13.110156202816112]
  This work introduces an innovative approach based on a structured state-space model (SSM), MambaTab, for tabular data. MambaTab delivers superior performance while requiring significantly fewer parameters, as empirically validated on diverse benchmark datasets.
  arXiv  Detail & Related papers  (2024-01-16T22:44:12Z)
• Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding [79.9461269253121]
  We propose the Chain-of-Table framework, where tabular data is explicitly used in the reasoning chain as a proxy for intermediate thoughts. Chain-of-Table achieves new state-of-the-art performance on WikiTQ, FeTaQA, and TabFact benchmarks.
  arXiv  Detail & Related papers  (2024-01-09T07:46:26Z)
• TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformers [56.56591337457137]
  We propose an accurate and end-to-end transformer-based table structure recognition method, referred to as TRUST. Transformers are suitable for table structure recognition because of their global computations, perfect memory, and parallel computation. We conduct experiments on several popular benchmarks including PubTabNet and SynthTable, our method achieves new state-of-the-art results.
  arXiv  Detail & Related papers  (2022-08-31T08:33:36Z)
• GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing [117.98107557103877]
  We present GraPPa, an effective pre-training approach for table semantic parsing. We construct synthetic question-pairs over high-free tables via a synchronous context-free grammar. To maintain the model's ability to represent real-world data, we also include masked language modeling.
  arXiv  Detail & Related papers  (2020-09-29T08:17:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.