AI Paper Atlas

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

BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language

Haitao Wu, Qirui Zhang, Zhouheng Yao, Shangquan Sun, Qihao Zheng, Mianxin Liu, Chi Zhang, Wanli Ouyang, Chunfeng Song, Changqing Zhang, Jiamin Wu

ICML 2026 · Vision-language and multimodal › Human and embodied modeling · approach: fMRI visual decoding · 0 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
train the model on brain-to-image pairs instead of only brain-to-text pairs (ablation)BrainJanus · NSD brain-to-image reconstructionCLIP: 77.3% -> 94.4%Improved
train the model on brain-to-image pairs instead of only brain-to-text pairs (ablation)BrainJanus · NSD brain-to-image reconstructionPixCorr: 0.077 -> 0.173Improved
use detailed Qwen captions as ground truth instead of short COCO captionsBrainJanus · NSD brain-to-captionBERT: 42.12 -> 38.12Mixed
use BrainJanus instead of MindLLM for brain-to-captionbrain-to-caption · NSD brain-to-caption (GT = Qwen detailed caption)CIDEr: 2.11 -> 41.32Improved
use BrainJanus instead of Transformer Encoding for brain encodingbrain encoding · NSD brain encoding (image branch)Inception: 70.4% -> 72.8%Improved
use autoregressive BrainJanus instead of diffusion-based MindEye2 for brain-to-imagebrain-to-image · NSD brain-to-image reconstructionPixCorr: 0.322 -> 0.173Hurt
use BrainJanus instead of MindEye2 for brain-to-imagebrain-to-image · NSD brain-to-image reconstructionCLIP: 93.0% -> 94.4%Improved
increase codebook size beyond 128 or 256 in the brain tokenizer (ablation)brain tokenizer · tokenizer ablationreconstruction and semantic metricsNo clear effect
zero-pad ground-truth visual embedding as fake fMRI (Padding Hacking)visual-to-fMRI evaluation protocol · visual-to-fMRI synthesisCLIP: 94.3% -> 100.0%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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