# Does Joint-Embedding Predictive Architecture Pretraining Help Time Series Forecasting?

arXiv: https://arxiv.org/abs/2609.31680 · HTML: https://mlsanity.com/paper/2609.31680/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 19 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 17 of 17)

- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Transformers in Time Series: A Survey](https://mlsanity.com/paper/2202.07125/) (2022)
- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting](https://mlsanity.com/paper/2202.01575/) (2022)
- [SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling](https://mlsanity.com/paper/2302.00861/) (2023)
- [Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects](https://mlsanity.com/paper/2306.10125/) (2023)
- [Transformers in Time-series Analysis: A Tutorial](https://mlsanity.com/paper/2205.01138/) (2022)
- [Joint Embeddings Go Temporal](https://mlsanity.com/paper/2509.25449/) (2025)
- [T-JEPA: A Joint-Embedding Predictive Architecture for Trajectory Similarity Computation](https://mlsanity.com/paper/2406.12913/) (2024)
- [Time-Series JEPA for Predictive Remote Control under Capacity-Limited Networks](https://mlsanity.com/paper/2406.04853/) (2024)
- [LaT-PFN: A Joint Embedding Predictive Architecture for In-context Time-series Forecasting](https://mlsanity.com/paper/2405.10093/) (2024)
- [HiT-JEPA: A Hierarchical Self-supervised Trajectory Embedding Framework for Similarity Computation](https://mlsanity.com/paper/2507.00028/) (2025)
- [LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning](https://mlsanity.com/paper/2607.00958/) (2026)
- [Is the reconstruction loss culprit? An attempt to outperform JEPA](https://mlsanity.com/paper/2603.14131/) (2026)

## Abstract (arXiv)

Joint-embedding predictive architectures (JEPA) have emerged as a promising self-supervised pretraining paradigm for time series, learning representations by predicting target embeddings in latent space rather than reconstructing raw signals. Yet evidence on their benefits remains mixed, and most studies test only a single backbone or a narrow set of architectures, leaving unclear whether JEPA pretraining is a reliable improvement or one that depends heavily on the downstream model. We address this gap through a large scale evaluation of one JEPA instantiation across nine backbones and eleven benchmarks spanning temporal and spatio-temporal forecasting, the most extensive cross architecture assessment of JEPA for time series to date. We find that the benefit of this instantiation varies sharply across backbones, producing consistent gains for some architectures and consistent degradation for others, even on the same dataset. This pattern holds across both task families, indicating the variability is a general property of this instantiation rather than a dataset specific artifact worth accounting for when choosing a backbone in practice.