# CF-JEPA: Mask-free forward prediction with asymmetric encoder utilization for time-series representation learning

arXiv: https://arxiv.org/abs/2606.07031 · HTML: https://mlsanity.com/paper/2606.07031/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [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)
- [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)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [Time-Series Representation Learning via Temporal and Contextual Contrasting](https://mlsanity.com/paper/2106.14112/) (2021)
- [Time Series Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2002.12478/) (2020)
- [Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications](https://mlsanity.com/paper/1802.03903/) (2018)
- [Time-Series Anomaly Detection Service at Microsoft](https://mlsanity.com/paper/1906.03821/) (2019)
- [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)
- [Time Series Contrastive Learning with Information-Aware Augmentations](https://mlsanity.com/paper/2303.11911/) (2023)
- [TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning](https://mlsanity.com/paper/2312.15709/) (2023)
- [Soft Contrastive Learning for Time Series](https://mlsanity.com/paper/2312.16424/) (2023)
- [T-Rep: Representation Learning for Time Series using Time-Embeddings](https://mlsanity.com/paper/2310.04486/) (2023)
- [Parametric Augmentation for Time Series Contrastive Learning](https://mlsanity.com/paper/2402.10434/) (2024)
- [Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning](https://mlsanity.com/paper/2412.20790/) (2024)
- [SC-JEPA: Stabilizing Latent Predictive Learning for Time-Series Anomaly Prediction](https://mlsanity.com/paper/2602.04643/) (2026)
- [FEATHer: Fourier-Efficient Adaptive Temporal Hierarchy Forecaster for Time-Series Forecasting](https://mlsanity.com/paper/2601.11350/) (2026)

## Built on by (most cited first, 1 of 1)

- [Phenomenon-Graph JEPA: Label-Efficient Representation Learning for Contactless Cardiorespiratory Sensing](https://mlsanity.com/paper/2609.32928/) (2026)

## Abstract (arXiv)

Self-supervised learning (SSL) for time-series representation learning is dominated by two paradigms: contrastive methods, which face challenges in constructing positive or negative pairs, and masking-based methods, which disrupt the temporal continuity of time-series signals. Joint-Embedding Predictive Architecture (JEPA) offers a promising alternative by predicting in representation space rather than reconstructing raw inputs. However, existing time-series JEPA variants still rely on masking and therefore inherit its continuity problem. Crop-based Forward JEPA (CF-JEPA) is proposed as an innovative mask-free framework that replaces masking with multi-horizon forward prediction: random crops serve as context views, and short-, mid-, and long-horizon future representations are predicted in the forward temporal direction, directly leveraging the inherent temporal ordering of time-series data as a learning signal. A strong asymmetry is also identified between the online encoder and the exponential moving average (EMA) target encoder, both produced from a single training run: the online encoder develops higher-rank discriminative features, while the EMA target encoder develops smoother, lower-rank temporal features. Exploiting this asymmetry, classification is routed to the online encoder and forecasting or anomaly detection to the EMA target encoder, achieving a 27% reduction in multivariate forecasting mean squared error (MSE) at no additional training cost. Across 126 University of California, Riverside (UCR) and 26 University of East Anglia (UEA) classification datasets, eight electricity transformer temperature forecasting benchmarks, and Key Performance Indicator /Yahoo anomaly detection, CF-JEPA achieves the highest average accuracy and rank on UCR and UEA among self-supervised baselines and ranks second on univariate forecasting and k-nearest neighbors-scored anomaly detection.