{"ID":2865082,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.00032","arxiv_id":"2510.00032","title":"WaveMind: Towards a Conversational EEG Foundation Model Aligned to Textual and Visual Modalities","abstract":"Electroencephalography (EEG) interpretation using multimodal large language models (MLLMs) offers a novel approach for analyzing brain signals. However, the complex nature of brain activity introduces critical challenges: EEG signals simultaneously encode both cognitive processes and intrinsic neural states, creating a mismatch in EEG paired-data modality that hinders effective cross-modal representation learning. Through a pivot investigation, we uncover complementary relationships between these modalities. Leveraging this insight, we propose mapping EEG signals and their corresponding modalities into a unified semantic space to achieve generalized interpretation. To fully enable conversational capabilities, we further introduce WaveMind-Instruct-338k, the first cross-task EEG dataset for instruction tuning. The resulting model demonstrates robust classification accuracy while supporting flexible, open-ended conversations across four downstream tasks, thereby offering valuable insights for both neuroscience research and the development of general-purpose EEG models.","short_abstract":"Electroencephalography (EEG) interpretation using multimodal large language models (MLLMs) offers a novel approach for analyzing brain signals. However, the complex nature of brain activity introduces critical challenges: EEG signals simultaneously encode both cognitive processes and intrinsic neural states, creating a...","url_abs":"https://arxiv.org/abs/2510.00032","url_pdf":"https://arxiv.org/pdf/2510.00032v1","authors":"[\"Ziyi Zeng\",\"Zhenyang Cai\",\"Yixi Cai\",\"Xidong Wang\",\"Junying Chen\",\"Rongsheng Wang\",\"Yipeng Liu\",\"Siqi Cai\",\"Benyou Wang\",\"Zhiguo Zhang\",\"Haizhou Li\"]","published":"2025-09-26T06:21:51Z","proceeding":"eess.SP","tasks":"[\"eess.SP\",\"cs.AI\",\"cs.CL\",\"cs.LG\",\"q-bio.NC\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}