AI Paper Atlas

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

A Cognitive Process-Inspired Architecture for Subject-Agnostic Brain Visual Decoding

Jingyu Lu, Haonan Wang, Qixiang ZHANG, Xiaomeng Li

ICLR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: fMRI visual decoding · 2 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
use VCFlow instead of GLFA* in subject-agnostic settingfMRI-to-video decoding · cc2017 averageframe 50-way accuracy: 9.6% -> 14.0%Improved
use VCFlow instead of subject-agnostic NEURONS*fMRI-to-video decoding · cc2017 averagevideo 50-way accuracy: 16.1% -> 18.2%Improved
use VCFlow (subject-agnostic) instead of subject-specific NEURONSfMRI-to-video decoding · cc2017 subject 1frame 50-way accuracy: 20.6% -> 14.2%Hurt
add image-pretraining to brain model (ablation)VCFlow ablation · cc2017 subject 1video 50-way accuracy: 12.6% -> 15.3%Improved
add HCAM to pretrained brain model (ablation)VCFlow ablation · cc2017 subject 1frame SSIM: 0.382 -> 0.357Hurt
add SARA after HCAM (ablation)VCFlow ablation · cc2017 subject 1CLIP-pcc: 0.919 -> 0.934Improved
add HED after SARA (ablation)VCFlow ablation · cc2017 subject 1video 50-way accuracy: 15.2% -> 18.9%Improved
add subject classification loss L_subj to SARA (ablation)VCFlow · cc2017 subject 1frame 50-way accuracy: 7.52% -> 10.7%Improved
add inter-subject contrastive loss L_generic to SARA (ablation)VCFlow · cc2017 subject 1frame 50-way accuracy: 10.7% -> 14.2%Improved
add motion loss to HED (ablation)VCFlow · cc2017 subject 1frame 50-way accuracy: 13.2% -> 11.3%Mixed
add classification loss to caption-only HED (ablation)VCFlow · cc2017 subject 1frame 50-way accuracy: 10.0% -> 8.2%Hurt

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