# Scalable Patch-Level Self-Supervised Learning

arXiv: https://arxiv.org/abs/2610.10013 · HTML: https://mlsanity.com/paper/2610.10013/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 73 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 8 of 8)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning](https://mlsanity.com/paper/2603.14482/) (2026)
- [Scaling Language-Free Visual Representation Learning](https://mlsanity.com/paper/2504.01017/) (2025)
- [Self-Supervised Learning by Estimating Twin Class Distributions](https://mlsanity.com/paper/2110.07402/) (2021)
- [Vision Pretraining for Dense Spatial Perception](https://mlsanity.com/paper/2607.05247/) (2026)
- [Self-Distillation of Hidden Layers for Self-Supervised Representation Learning](https://mlsanity.com/paper/2603.15553/) (2026)

## Abstract (arXiv)

Self-supervised learning (SSL) at scale produces powerful visual representations. However, most scalable SSL methods rely on ad hoc combinations of multiple objectives and stabilization mechanisms. Taking a step back, we ask if we can design a high-performing, yet principled SSL algorithm. Starting from the multi-view assumption, stipulating that task-relevant content is captured by the information common to different views, we construct an information-theoretic objective decomposing into interpretable terms. This derivation yields JEM, a student-teacher method that learns by aligning corresponding patch representations across views, explicitly regularized by information and structure preservation losses. JEM trains stably from 300M to 7B parameters, and, to our knowledge, is the first latent-space patch-level method demonstrated at 7B scale. Across all scales, JEM reaches strong performance on both global and dense probing tasks, on segmentation benchmarks consistently surpassing the DINOv2 algorithm, an influential foundation for today's strongest visual SSL methods. Notably, at 7B parameters, it exceeds the performance of DINOv3 on panoptic segmentation, despite being trained on 12× less data without refinement stages. These results demonstrate that we can indeed design an SSL algorithm that learns strong representations, is principled and stable.