SOURCE-LINKED INTELLIGENCE

HDND: Hierarchical Dynamic Neural Decoding for Multilingual Word/Character Retrieval from Non-Invasive Brain Recordings

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

While deep learning has enabled language decoding from intracranial brain recordings, extending this capability to non-invasive recordings remains an unresolved challenge. Decoding individual words from non-invasive brain recordings is particularly difficult, as word-level neural evidence is weak, temporally distributed, and entangled with acoustic, lexical, and semantic structure. Existing retrieval pipelines often collapse these factors into a single representation, potentially discarding information available at intermediate temporal scales. Here, we introduce Hierarchical Dynamic Neural De

Read original source ↗ Open in workspace

recordType

paper

region

Global