CGM-JEPA learns transferable CGM representations via predictive self-supervised pretraining on unlabeled time series and cross-view distributional objectives, outperforming baselines on AUROC for insulin resistance and beta-cell dysfunction across modality shifts and cohorts.
A simple framework for contrastive learning of visual representations
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
DeepSignature embeds digitally signed content-encoding watermarks via neural networks for robust image authentication, source attribution, and latent-space tamper localization.
AML outperforms cross-validated baselines including CNNs on 50-2000 example image datasets and is comparable to XGBoost/LightGBM on tabular data using only training data and no task-dependent hyperparameters.
citing papers explorer
-
CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining
CGM-JEPA learns transferable CGM representations via predictive self-supervised pretraining on unlabeled time series and cross-view distributional objectives, outperforming baselines on AUROC for insulin resistance and beta-cell dysfunction across modality shifts and cohorts.
-
DeepSignature: Digitally Signed, Content-Encoding Watermarks for Robust and Transparent Image Authentication
DeepSignature embeds digitally signed content-encoding watermarks via neural networks for robust image authentication, source attribution, and latent-space tamper localization.
-
Algebraic Machine Learning for Small-to-Medium Datasets Is Competitive against Strong Standard Baselines
AML outperforms cross-validated baselines including CNNs on 50-2000 example image datasets and is comparable to XGBoost/LightGBM on tabular data using only training data and no task-dependent hyperparameters.