Event identification in continuous neural recordings is a critical task in neuroscience. Decoding in EEG is dominated by classifying windows aligned to known event onsets. However, while available in controlled experiments, such onsets are absent in continuous real-world monitoring. Here, we introduce DANCE, a deep learning pipeline that frames neural decoding as a set-prediction problem and jointly detects and classifies events directly from raw, unaligned signals. Evaluated separately on ten datasets curated from the literature with a wide variety of event types (ranging from milliseconds to minutes in duration), our model outperforms existing methods on a broad range of cognitive, clinical and BCI tasks. This single architecture establishes a new state of the art in the competitive task of seizure monitoring and matches the accuracy of onset-informed models for BCI tasks. Overall, our method marks a step towards end-to-end asynchronous neural decoding models
@article{arxiv.2605.10688,
title = {DANCE: Detect and Classify Events in EEG},
author = {Jarod Lévy and Hubert Banville and Jérémy Rapin and Jean-Remi King and Thomas Moreau and Stéphane d'Ascoli},
journal= {arXiv preprint arXiv:2605.10688},
year = {2026}
}