# TabICLv2: A better, faster, scalable, and open tabular foundation model

arXiv: https://arxiv.org/abs/2602.11139 · HTML: https://mlsanity.com/paper/2602.11139/

## Key facts

- Cited by 144 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2026.

## Built on by (most cited first, 30 of 144)

- [Beyond IID: How General Are Tabular Foundation Models, Really?](https://mlsanity.com/paper/2606.30410/) (2026)
- [KumoRFM-2: Scaling Foundation Models for Relational Learning](https://mlsanity.com/paper/2604.12596/) (2026)
- [EXAONE Tabular 1.0 : Technical Report](https://mlsanity.com/paper/2608.25774/) (2026)
- [LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence](https://mlsanity.com/paper/2609.17488/) (2026)
- [ScoringBench: A Benchmark for Evaluating Tabular Foundation Models with Proper Scoring Rules](https://mlsanity.com/paper/2603.29928/) (2026)
- [Tabular foundation models for in-context prediction of molecular properties](https://mlsanity.com/paper/2604.16123/) (2026)
- [Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality](https://mlsanity.com/paper/2605.18971/) (2026)
- [TabDPT-Turbo: Efficient In-Context Learning for Tabular Prediction](https://mlsanity.com/paper/2608.01400/) (2026)
- [TabFM: A Zero-Shot Foundation Model for Tabular Data](https://mlsanity.com/paper/2609.37959/) (2026)
- [Benchmarking Optimizers for MLPs in Tabular Deep Learning](https://mlsanity.com/paper/2604.15297/) (2026)
- [STRABLE: Benchmarking Tabular Machine Learning with Strings](https://mlsanity.com/paper/2605.12292/) (2026)
- [Causal Foundation Models with Continuous Treatments](https://mlsanity.com/paper/2605.15133/) (2026)
- [SurvPFN: Towards Foundation Models for Survival Predictions](https://mlsanity.com/paper/2606.04564/) (2026)
- [TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning](https://mlsanity.com/paper/2606.05878/) (2026)
- [A Fair Evaluation of Graph Foundation Models for Node Property Prediction](https://mlsanity.com/paper/2606.24509/) (2026)
- [TACTICL: Task-Aware Compression of Tabular ICL Models](https://mlsanity.com/paper/2608.10837/) (2026)
- [Mitra-v2 Technical Report](https://mlsanity.com/paper/2609.04540/) (2026)
- [Distributional Regression with Tabular Foundation Models: Evaluating Probabilistic Predictions via Proper Scoring Rules](https://mlsanity.com/paper/2603.08206/) (2026)
- [Benchmarking Tabular Foundation Models for Conditional Density Estimation in Regression](https://mlsanity.com/paper/2603.26611/) (2026)
- [RamanBench: A Large-Scale Benchmark for Machine Learning on Raman Spectroscopy](https://mlsanity.com/paper/2605.02003/) (2026)
- [Scaling Limits of Long-Context Transformers](https://mlsanity.com/paper/2605.08505/) (2026)
- [TabFORGE: A Tabular Foundation Model for Generative Modelling](https://mlsanity.com/paper/2605.09424/) (2026)
- [VIP-COP: Context Optimization for Tabular Foundation Models](https://mlsanity.com/paper/2605.12904/) (2026)
- [SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference](https://mlsanity.com/paper/2605.15488/) (2026)
- [TabH2O: A Unified Foundation Model for Tabular Prediction](https://mlsanity.com/paper/2605.18383/) (2026)
- [On the Diverse Dynamical Behaviors Arising in Deep Linear Transformers](https://mlsanity.com/paper/2607.18584/) (2026)
- [Causilo Technical Report](https://mlsanity.com/paper/2609.22866/) (2026)
- [In-Context Black-Box Optimization with Unreliable Feedback](https://mlsanity.com/paper/2605.06187/) (2026)
- [PFN-TS: Thompson Sampling for Contextual Bandits via Prior-Data Fitted Networks](https://mlsanity.com/paper/2605.10137/) (2026)
- [MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image](https://mlsanity.com/paper/2605.10616/) (2026)

## Abstract (arXiv)

Tabular foundation models, such as TabPFNv2 and TabICL, have recently dethroned gradient-boosted trees at the top of predictive benchmarks, demonstrating the value of in-context learning for tabular data. We introduce TabICLv2, a new state-of-the-art foundation model for regression and classification built on three pillars: (1) a novel synthetic data generation engine designed for high pretraining diversity; (2) various architectural innovations, including a new scalable softmax in attention improving generalization to larger datasets without prohibitive long-sequence pretraining; and (3) optimized pretraining protocols, notably replacing AdamW with the Muon optimizer. On the TabArena and TALENT benchmarks, TabICLv2 without any tuning surpasses the performance of the current state of the art, RealTabPFN-2.5 (hyperparameter-tuned, ensembled, and fine-tuned on real data). With only moderate pretraining compute, TabICLv2 generalizes effectively to million-scale datasets under 50 GB GPU memory while being markedly faster than RealTabPFN-2.5. We provide extensive ablation studies to quantify these contributions and foster open research by releasing code for inference, pretraining, and synthetic data generation at https://github.com/soda-inria/tabicl.