{"ID":2842798,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.09250","arxiv_id":"2511.09250","title":"NeuroCLIP: Brain-Inspired Prompt Tuning for EEG-to-Image Multimodal Contrastive Learning","abstract":"Recent advances in brain-inspired artificial intelligence have sought to align neural signals with visual semantics using multimodal models such as CLIP. However, existing methods often treat CLIP as a static feature extractor, overlooking its adaptability to neural representations and the inherent physiological-symbolic gap in EEG-image alignment. To address these challenges, we present NeuroCLIP, a prompt tuning framework tailored for EEG-to-image contrastive learning. Our approach introduces three core innovations: (1) We design a dual-stream visual embedding pipeline that combines dynamic filtering and token-level fusion to generate instance-level adaptive prompts, which guide the adjustment of patch embedding tokens based on image content, thereby enabling fine-grained modulation of visual representations under neural constraints; (2) We are the first to introduce visual prompt tokens into EEG-image alignment, acting as global, modality-level prompts that work in conjunction with instance-level adjustments. These visual prompt tokens are inserted into the Transformer architecture to facilitate neural-aware adaptation and parameter optimization at a global level; (3) Inspired by neuroscientific principles of human visual encoding, we propose a refined contrastive loss that better model the semantic ambiguity and cross-modal noise present in EEG signals. On the THINGS-EEG2 dataset, NeuroCLIP achieves a Top-1 accuracy of 63.2% in zero-shot image retrieval, surpassing the previous best method by +12.3%, and demonstrates strong generalization under inter-subject conditions (+4.6% Top-1), highlighting the potential of physiology-aware prompt tuning for bridging brain signals and visual semantics.","short_abstract":"Recent advances in brain-inspired artificial intelligence have sought to align neural signals with visual semantics using multimodal models such as CLIP. However, existing methods often treat CLIP as a static feature extractor, overlooking its adaptability to neural representations and the inherent physiological-symbol...","url_abs":"https://arxiv.org/abs/2511.09250","url_pdf":"https://arxiv.org/pdf/2511.09250v1","authors":"[\"Jiyuan Wang\",\"Li Zhang\",\"Haipeng Lin\",\"Qile Liu\",\"Gan Huang\",\"Ziyu Li\",\"Zhen Liang\",\"Xia Wu\"]","published":"2025-11-12T12:13:24Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"Transformer\"]","has_code":false}