Tag
The paper proposes BLPM, an EEG-language foundation model that uses continuous latent predictive modeling and semantic alignment to map EEG signals to text embeddings, achieving generalizable neural decoding across diverse tasks and datasets.
CellWorld introduces a latent-space predictive pretraining approach for spatial transcriptomics foundation models, predicting latent representations of masked cells instead of reconstructing gene measurements. Across held-out datasets, even small variants outperform existing baselines on all benchmarks, showing that scaling and broad biological diversity improve transferability.
This paper introduces NodeJEPA, a joint-embedding predictive architecture for node-level graph self-supervised learning that predicts latent representations of masked structure-aware ego-subgraphs, avoiding reconstruction and hand-crafted augmentations. The method is evaluated on node classification benchmarks and shows competitive performance.
This paper analyzes why deterministic JEPA-style latent prediction works for images but not for text, attributing the failure to high conditional variance in language where masked contexts admit multiple valid completions whose representations lack a coherent center.
This paper proves that learning by predicting latent representations (as in world models like JEPA and data2vec) requires exponentially less data than predicting tokens (as in LLMs) for hierarchical data with hidden structure.