aiqbench analysis
This research introduces the Morlet Spectral Transformer (MST), a novel architecture designed to improve cross-subject emotion decoding from EEG data by integrating spectral context without relying on external pretraining. By conditioning target tokens on structured spectral summaries, MST effectively balances the retention of absolute neural activity with the incorporation of neighboring window information, achieving state-of-the-art accuracy on standard benchmarks like SEED and FACED. The study demonstrates that this approach outperforms both pretrained models and from-scratch baselines, offering a robust method for handling background variation in brain-computer interface applications.
Context-aware tokenization for Cross-subject Emotion Decoding from EEG
arXiv:2606.00884v2 Announce Type: replace Abstract: In cross-subject EEG emotion decoding, neighboring windows can inform the representation of a target window, but they contain both background variation and sustained task signals. This creates a challenge for contextual representation learning because subtracting shared activity can also remove useful information. We introduce the Morlet Spectral Transformer (MST), which conditions target-window tokens on a structured spectral summary before attention. MST averages the Morlet log-amplitude spectra of unlabeled same-trial neighbors and uses frequency-specific electrode projections to combine the target spectrum with its reference-relative residual. This retains access to absolute activity while incorporating context into a fixed attended target-token grid. Without external pretraining, MST achieves 66.5\%, 40.7\%, 36.1\%, and 27.9\% accuracy on SEED, SEED-IV, SEED-V, and SEED-VII under leave-one-subject-out evaluation, averaged over three random seeds, outperforming the evaluated pretrained and from-scratch baselines. On FACED, MST achieves 17.52\% accuracy in nine-class cross-subject evaluation, exceeding the strongest evaluated baseline by 1.15 percentage points. We also performed the ablation studies across all 15 SEED subjects to evaluate the contribution of different components of MST.
Abstract:In cross-subject EEG emotion decoding, neighboring windows can inform the representation of a target window, but they contain both background variation and sustained task signals. This creates a challenge for contextual representation learning because subtracting shared activity can also remove useful information. We introduce the Morlet Spectral Transformer (MST), which conditions target-window tokens on a structured spectral summary before attention. MST averages the Morlet log-amplitude spectra of unlabeled same-trial neighbors and uses frequency-specific electrode projections to combine the target spectrum with its reference-relative residual. This retains access to absolute activity while incorporating context into a fixed attended target-token grid. Without external pretraining, MST achieves 66.5\%, 40.7\%, 36.1\%, and 27.9\% accuracy on SEED, SEED-IV, SEED-V, and SEED-VII under leave-one-subject-out evaluation, averaged over three random seeds, outperforming the evaluated pretrained and from-scratch baselines. On FACED, MST achieves 17.52\% accuracy in nine-class cross-subject evaluation, exceeding the strongest evaluated baseline by 1.15 percentage points. We also performed the ablation studies across all 15 SEED subjects to evaluate the contribution of different components of MST.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2606.00884 [cs.LG]
(or arXiv:2606.00884v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.00884 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 265 words
Related coverage
Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
METR · Aug 26, 2026
Benchmarking Kimi-K3 Across vLLM, SGLang, and ATOM on MI350X
AMD · Sep 22, 2026
Construct validity of Claude Opus 4.8's System Card – A commentary
LessWrong · Jun 12, 2026
DI Series: Scaling GLM-5.1-FP8 to 64 MI300X GPUs
AMD · Aug 21, 2026