NeuroscienceInformation FusionPeer-reviewed
From Sight to Insight: A Multi-task Approach with the Visual Language Decoding Model
Wei Huang, Pengfei Yang, Ying Tang…·Huafu Chen
This paper introduces a Visual Language Decoding Model (VLDM) that simultaneously decodes visual categories, semantic labels, and textual descriptions from neural data, achieving significant improvements over chance levels.
19 citationstop 4%