# Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture - Bridging Predictive and Generative Self-Supervised Learning

arXiv: https://arxiv.org/abs/2603.20111 · HTML: https://mlsanity.com/paper/2603.20111/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems](https://mlsanity.com/paper/2008.13535/) (2020)
- [AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks](https://mlsanity.com/paper/1810.11921/) (2018)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models](https://mlsanity.com/paper/2601.14354/) (2026)
- [Video Representation Learning with Joint-Embedding Predictive Architectures](https://mlsanity.com/paper/2412.10925/) (2024)
- [T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data](https://mlsanity.com/paper/2410.05016/) (2024)
- [Coupled Variational Autoencoder](https://mlsanity.com/paper/2306.02565/) (2023)
- [Brain-Inspired Stochastic Joint Embedding Representation Learning](https://mlsanity.com/paper/2505.11129/) (2025)

## Built on by (most cited first, 4 of 4)

- [The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models](https://mlsanity.com/paper/2607.13612/) (2026)
- [Output-Level Regularization Eliminates the Seed Lottery in Single-GPU VLA Fine-Tuning](https://mlsanity.com/paper/2606.13856/) (2026)
- [The JEPA Predictor: A Transferable Operator for Occluded Feature Completion](https://mlsanity.com/paper/2607.16274/) (2026)
- [D-JEPA: A Decision-Aligned Latent World Model](https://mlsanity.com/paper/2609.24749/) (2026)

## Abstract (arXiv)

The Joint-Embedding Predictive Architecture (JEPA) is often seen as a non-generative alternative to likelihood-based self-supervised learning, emphasizing prediction in representation space rather than reconstruction in observation space. We argue that the resulting separation from probabilistic generative modeling is largely rhetorical rather than structural: the canonical JEPA design (coupled encoders with a context-to-target predictor) mirrors the variational posteriors and learned conditional priors obtained when variational inference is applied to a particular class of coupled latent-variable models, and standard JEPA can be viewed as a deterministic specialization in which regularization is imposed via architectural and training heuristics rather than an explicit likelihood. Building on this view, we derive the Variational JEPA (Var-JEPA), which makes the latent generative structure explicit by optimizing a single Evidence Lower Bound (ELBO). This yields meaningful representations without ad-hoc anti-collapse regularizers and allows principled uncertainty quantification in the latent space. We instantiate the framework for tabular data (Var-T-JEPA) and achieve strong representation learning and downstream performance, improving over T-JEPA across real-world tabular benchmarks while remaining competitive with strong raw-feature baselines.