# A JEPA Recipe for Tabular Foundation Models

arXiv: https://arxiv.org/abs/2609.25541 · HTML: https://mlsanity.com/paper/2609.25541/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 28 of its 33 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 28 of 28)

- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [Understanding Dimensional Collapse in Contrastive Self-supervised Learning](https://mlsanity.com/paper/2110.09348/) (2021)
- [Transformers Can Do Bayesian Inference](https://mlsanity.com/paper/2112.10510/) (2021)
- [SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training](https://mlsanity.com/paper/2106.01342/) (2021)
- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [OpenML Benchmarking Suites](https://mlsanity.com/paper/1708.03731/) (2017)
- [TabArena: A Living Benchmark for Machine Learning on Tabular Data](https://mlsanity.com/paper/2506.16791/) (2025)
- [SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption](https://mlsanity.com/paper/2106.15147/) (2021)
- [RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank](https://mlsanity.com/paper/2210.02885/) (2022)
- [TransTab: Learning Transferable Tabular Transformers Across Tables](https://mlsanity.com/paper/2205.09328/) (2022)
- [TabDPT: Scaling Tabular Foundation Models on Real Data](https://mlsanity.com/paper/2410.18164/) (2024)
- [Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language](https://mlsanity.com/paper/2212.07525/) (2022)
- [SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning](https://mlsanity.com/paper/2110.04361/) (2021)
- [Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models](https://mlsanity.com/paper/2510.21204/) (2025)
- [CARTE: Pretraining and Transfer for Tabular Learning](https://mlsanity.com/paper/2402.16785/) (2024)
- [STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables](https://mlsanity.com/paper/2303.00918/) (2023)
- [How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks](https://mlsanity.com/paper/2407.03475/) (2024)
- [LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures](https://mlsanity.com/paper/2312.04000/) (2023)
- [T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data](https://mlsanity.com/paper/2410.05016/) (2024)
- [Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality](https://mlsanity.com/paper/2605.18971/) (2026)

## Abstract (arXiv)

Tabular foundation models learn to predict cell values in context, whereas world-model self-supervision asks for prediction in representation space (LeCun, 2022; Assran et al., 2023). On a tabular foundation-model prior, the latent term of a joint-embedding predictive architecture (JEPA) collapsed in our earlier runs and took the encoder with it to a constant map. We report a recipe under which the latent term survives to convergence beside the value objective: the value head reads the encoder field rather than the predictor, and the target is an exponential moving average (EMA) difference. To bound its cost against the value-only arm, both arms train until a plateau rule stops them, with no fixed step budget. A fixed horizon had confounded a slowdown with a ceiling, since the value-only arm was still improving well past the usual budget. At convergence, in one run per arm, the JEPA arm trails the value-only arm across 147 real datasets, 32:70 wins to losses on classification (29:63 with one entry per dataset name) and 8:24 on regression, the margin small on classification and wider on regression, and the count leans the same way in each stratum and each benchmark. The JEPA arm (jepa) needs 1.42 times as many steps as the value-only arm (ds), and 1.66 times its wall-clock, to reach its plateau.