TabSieve is a select‑then‑predict framework that explicitly chooses a small set of informative rows from a table as evidence before predicting a missing target. The authors build a large synthetic dataset, TabSieve‑SFT‑40K, and introduce a reinforcement learning method, TAB‑GRPO, to jointly optimize evidence selection and prediction. Experiments on 75 classification and 52 regression tables show consistent performance gains, with TabSieve improving classification by 2.92% and regression by 4.45% over the best baseline while enhancing robustness to noisy context.
arXiv:2609.37959v1 Announce Type: new Abstract: Tabular machine learning typically relies on per-dataset workflows, fitting tree ensembles or running AutoML searches from scratch for every task. We p...
Xiaomi-TabLDM is a tabular foundation model that performs classification and regression via in-context learning without task‑specific fine‑tuning. It is pretrained solely on synthetic data from structural causal models, achieving top‑ranked regression results on multiple benchmarks while reducing training and prediction time compared to leading models. The architecture incorporates a three‑stage training strategy, dual‑stream feature grouping, lightweight attention residuals, and sparse mixture‑of‑experts, and it can further improve accuracy through test‑time compute scaling.
arXiv:2605. 18383v2 Announce Type: replace Abstract: We present TabH2O, a foundation model for tabular data that performs classification and regression in a single forward pass via in-context learning.
arXiv:2605. 24417v2 Announce Type: replace Abstract: Supervised classification on tabular data remains a central machine learning task, but its dependence on large labeled datasets limits its applicability in data-scarce settings.
ARASH is a method that improves the efficiency of Tabular Foundation Models by selecting optimal few-shot prompts based on local neighborhood analysis within the training set. It reduces the prompt length and memory usage of TabPFN by 1261.5× and 2.56×, respectively, while maintaining comparable accuracy. This approach addresses the challenge of identifying relevant rows for in-context learning in tabular data.
arXiv:2606. 32029v1 Announce Type: cross Abstract: While large language models (LLMs) perform well on table tasks, they still make data referencing errors (DREs), i.
The paper investigates how Tabular Foundation Models (TFMs) can achieve strong transfer learning by self‑supervised pre‑training on a single real table. It finds that a table’s usefulness is largely determined by its number of features rather than instances, and that fine‑grained column‑level preprocessing improves downstream performance while dataset‑level filtering does not. The authors propose that tabular in‑context generalization is primarily retrieval‑based, with models learning to identify and aggregate relevant examples from the provided context.
arXiv:2606. 04503v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has greatly advanced large reasoning models (LRMs), but it requires timely training on a huge fully-annotated dataset.
The paper investigates how Tabular Foundation Models (TFMs) can achieve strong transfer learning by self‑supervised pre‑training on a single real table, rather than large synthetic or real datasets. It finds that a table’s usefulness for downstream tasks is mainly determined by the number of features, not instances, and that fine‑grained column‑level preprocessing improves performance while dataset‑level filtering does not. The authors propose a task‑centric, retrieval‑based view of in‑context generalization, suggesting that effective TFMs identify and aggregate relevant examples from the provided context.
arXiv:2606. 09078v1 Announce Type: new Abstract: Process Reward Models (PRMs) improve credit assignment for reasoning by providing step-level feedback.
arXiv:2606. 29481v1 Announce Type: cross Abstract: While reinforcement learning (RL) significantly enhances LLM reasoning, its efficacy is severely undermined by Pre-RL data overlap, where RL datasets overlap with pretraining or SFT corpora, causing models to exploit shortcuts by memorizing correct answers and fabricating post-hoc reasoning.
arXiv:2603. 25184v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks.