sEEG-based Encoding for Sentence Retrieval: A Contrastive Learning Approach to Brain-Language Alignment

Interpreting neural activity through meaningful latent representations remains a complex and evolving challenge at the intersection of neuroscience and artificial intelligence. W e investigate the potential of multimodal foundation models to align invasive brain recordings with natural language. W e present SSENSE, a contrastive learning framework that projects single-subject stereo-electroencephalography (sEEG) signals into the sentence embedding space of a frozen CLIP model, enabling sentence-level retrieval directly from brain activity. SSENSE trains a neural encoder on spectral representations of sEEG using InfoNCE loss, without fine-tuning the text encoder . W e evaluate our method on time-aligned sEEG and spoken transcripts from a naturalistic movie-watching dataset. Despite limited data, SSENSE achieves promising results, demonstrating that general-purpose language representations can serve as effective priors for neural decoding.