AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Seeing Through the Brain: New Insights from Decoding Visual Stimuli with fMRI

Zheng Huang, Enpei Zhang, Weikang Qiu, Yinghao Cai, Carl Yang, Elynn Chen, Xiang Zhang, Rex Ying, Dawei Zhou, Yujun Yan

ICLR 2026 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 5 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
add object-centric cross-attention (ablation)fMRI-to-image framework · NSDLPIPS: 0.6111 -> 0.5963Improved
add object-centric cross-attention (ablation)fMRI-to-image framework · NSDSSIM: 0.4299 -> 0.4640Improved
add attribute/relationship prompt search instead of best initial keyword (ablation)fMRI-to-image framework · NSDSSIM: 0.4421 -> 0.4640Improved
add prompt search instead of worst initial keyword (ablation)fMRI-to-image framework · NSDLPIPS: 0.6398 -> 0.5963Improved
use LM text space as latent instead of CLIP text (ablation)fMRI-to-image framework · NSDLPIPS: 0.6611 -> 0.5963Improved
use LM text space as latent instead of LDM image latent (ablation)fMRI-to-image framework · NSDLPIPS: 0.7502 -> 0.5963Improved
use two objects instead of one (ablation)fMRI-to-image framework · NSDLPIPS: 0.6014 -> 0.5943Improved
use two objects instead of four (ablation)fMRI-to-image framework · NSDLPIPS: 0.6284 -> 0.5943Improved
swap Stable Diffusion 2.1 backbone for SDXLfMRI-to-image framework · NSDLPIPS: 0.5963 -> 0.5563Improved
compare T5 text space to ResNet50 vision space for fMRI alignmentrepresentation spaces · fMRI-representation alignmentCKA: 0.1822 -> 0.5580Improved
compare T5 text space to ResNet50 for learnabilityrepresentation spaces · fMRI-representation alignmentGeneralization Gap: 1.9800 -> 0.1132Improved
use the method instead of Mindeye2 for QA on reconstructionsfMRI decoders · NSD image QAaccuracy: 0.5765 -> 0.6054Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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