AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

MindSight: A Bio-Inspired Neural Architecture for Visual Restoration via Cortical Electrical Stimulation

Yongjie Zou, Haonan Niu, Bin Zhao, Guoliang Yi, Mengchuanzhi Yang, Jiawei Ju, Jiapeng Yin, Chengyu T. Li

AAAI 2026 · Vision-language and multimodal › Human and embodied modeling · approach: fMRI visual decoding · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
remove electrical stimulation from ESG in monkey delayed match-to-sample (ablation)MindSight · Two-class DMS (monkeys)behavioral success rate: high accuracy -> chance levelHurt
stimulate with MindSight ESG versus no-stimulation control (ablation)MindSight · Four-class DMS (monkeys 22, 23)behavioral success rate: above 25% chanceImproved
use MID decoder instead of SID, UNet-based and DGMM decodersMUA-Image Decoder · NIVD test setMSE, SSIM, PSNRImproved
use MindSight versus Chen et al. 2020 protocolcortical stimulation method · Two-class DMSaccuracy stabilityImproved
worse electrode placement (VM15 versus VM22)MindSight ESG · Simulated phosphene vs targetIoU: Triangle IoU 0.60 -> 0.43Hurt
add background gated network to filter irrelevant inputs (ablation)MindSight · Driving obstacle-avoidance foraging (DOAF)stimulation only on key cuesImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy