{"ID":2856978,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.10004","arxiv_id":"2510.10004","title":"Bidirectional Time-Frequency Pyramid Network for Enhanced Robust EEG Classification","abstract":"Existing EEG recognition models suffer from poor cross-paradigm generalization due to dataset-specific constraints and individual variability. To overcome these limitations, we propose BITE (Bidirectional Time-Freq Pyramid Network), an end-to-end unified architecture featuring robust multistream synergy, pyramid time-frequency attention (PTFA), and bidirectional adaptive convolutions. The framework uniquely integrates: 1) Aligned time-frequency streams maintaining temporal synchronization with STFT for bidirectional modeling, 2) PTFA-based multi-scale feature enhancement amplifying critical neural patterns, 3) BiTCN with learnable fusion capturing forward/backward neural dynamics. Demonstrating enhanced robustness, BITE achieves state-of-the-art performance across four divergent paradigms (BCICIV-2A/2B, HGD, SD-SSVEP), excelling in both within-subject accuracy and cross-subject generalization. As a unified architecture, it combines robust performance across both MI and SSVEP tasks with exceptional computational efficiency. Our work validates that paradigm-aligned spectral-temporal processing is essential for reliable BCI systems. Just as its name suggests, BITE \"takes a bite out of EEG.\" The source code is available at https://github.com/cindy-hong/BiteEEG.","short_abstract":"Existing EEG recognition models suffer from poor cross-paradigm generalization due to dataset-specific constraints and individual variability. To overcome these limitations, we propose BITE (Bidirectional Time-Freq Pyramid Network), an end-to-end unified architecture featuring robust multistream synergy, pyramid time-f...","url_abs":"https://arxiv.org/abs/2510.10004","url_pdf":"https://arxiv.org/pdf/2510.10004v2","authors":"[\"Jiahui Hong\",\"Siqing Li\",\"Muqing Jian\",\"Luming Yang\"]","published":"2025-10-11T04:14:48Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":608399,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2856978,"paper_url":"https://arxiv.org/abs/2510.10004","paper_title":"Bidirectional Time-Frequency Pyramid Network for Enhanced Robust EEG Classification","repo_url":"https://github.com/cindy-hong/BiteEEG","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}