# CoJEPA: Combining Contrastive Learning and JEPA for Global-Local Music Representations

arXiv: https://arxiv.org/abs/2608.30974 · HTML: https://mlsanity.com/paper/2608.30974/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 38 of its 50 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 30 of 38)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [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)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [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)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [Understanding self-supervised Learning Dynamics without Contrastive Pairs](https://mlsanity.com/paper/2102.06810/) (2021)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training](https://mlsanity.com/paper/2306.00107/) (2023)
- [Contrastive Audio-Visual Masked Autoencoder](https://mlsanity.com/paper/2210.07839/) (2022)
- [Contrastive Learning of Musical Representations](https://mlsanity.com/paper/2103.09410/) (2021)
- [A Foundation Model for Music Informatics](https://mlsanity.com/paper/2311.03318/) (2023)
- [Supervised and Unsupervised Learning of Audio Representations for Music Understanding](https://mlsanity.com/paper/2210.03799/) (2022)
- [Sample-level Deep Convolutional Neural Networks for Music Auto-tagging Using Raw Waveforms](https://mlsanity.com/paper/1703.01789/) (2017)
- [SPICE: Self-supervised Pitch Estimation](https://mlsanity.com/paper/1910.11664/) (2019)
- [Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learning](https://mlsanity.com/paper/2410.19560/) (2024)
- [PESTO: Pitch Estimation with Self-supervised Transposition-equivariant Objective](https://mlsanity.com/paper/2309.02265/) (2023)
- [Enriched Music Representations with Multiple Cross-modal Contrastive Learning](https://mlsanity.com/paper/2104.00437/) (2021)
- [Equivariant Self-Supervision for Musical Tempo Estimation](https://mlsanity.com/paper/2209.01478/) (2022)
- [STONE: Self-supervised Tonality Estimator](https://mlsanity.com/paper/2407.07408/) (2024)
- [Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation](https://mlsanity.com/paper/2408.02514/) (2024)
- [MATPAC++: Enhanced Masked Latent Prediction for Self-Supervised Audio Representation Learning](https://mlsanity.com/paper/2508.12709/) (2025)
- [Toward Fully Self-Supervised Multi-Pitch Estimation](https://mlsanity.com/paper/2402.15569/) (2024)

## Abstract (arXiv)

Joint-Embedding Predictive Architecture (JEPA) has shown strong performance in learning rich representations through self-supervised prediction in latent space. However, it typically relies on teacher--student architecture with an EMA to stabilise training, and can tend to yield uninformative representations. Contrastive learning is stable to train and produces strong global representations, but remains limited on local tasks by the global nature of its objective. In this work, we combine both into CoJEPA: a single shared backbone jointly trained with a JEPA objective on masked sequence tokens and a contrastive objective on the class token. The contrastive gradient provides stability, removing the need for an EMA teacher entirely, while JEPA enriches the sequence tokens via local predictions that contrastive learning alone cannot provide. Crucially, no extra parameters are added to the backbone: the same model is guided towards richer representations purely through the design of its training signal. CoJEPA takes the best of both worlds, outperforming or matching both individual methods across global and local MIR tasks, with a particularly strong advantage on tonal and harmonic understanding, and without any task-specific architectural changes. CoJEPA shows that combining objectives with complementary inductive biases can substitute for scale, encouraging future work to invest in smarter training objectives over ever-larger models.