Next-token prediction on multi-modal tokenized sleep signals yields embeddings that match supervised performance with far less labels and generalize to daytime heart data.
Chén, Philipp Koch, Alfred Mertins, and Maarten De Vos
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Microstate tokenizer from clustered EEG signals provides universal representations that outperform traditional time- and frequency-domain features across sleep staging, emotion recognition, and motor imagery tasks.
Randomly initialized Transformers act as adaptive sequence smoothers for sleep staging via a Random Attention Prior Kernel, with gains mainly from inductive bias rather than training.
citing papers explorer
-
Next-Token Prediction Learns Generalisable Representations of Sleep Physiology
Next-token prediction on multi-modal tokenized sleep signals yields embeddings that match supervised performance with far less labels and generalize to daytime heart data.
-
Atoms of Thought: Universal EEG Representation Learning with Microstates
Microstate tokenizer from clustered EEG signals provides universal representations that outperform traditional time- and frequency-domain features across sleep staging, emotion recognition, and motor imagery tasks.
-
Rethinking Random Transformers as Adaptive Sequence Smoothers for Sleep Staging
Randomly initialized Transformers act as adaptive sequence smoothers for sleep staging via a Random Attention Prior Kernel, with gains mainly from inductive bias rather than training.