AI Paper Atlas

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

Assembling the Mind's Mosaic: Towards EEG Semantic Intent Decoding

Jiahe Li, Junru Chen, Fanqi Shen, Jialan Yang, Jada Li, Zhizhang Yuan, Baowen Cheng, Meng Li, Yang Yang

ICLR 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
add set-based semantic decomposer (bipartite set matching) (ablation)BrainMosaic · Clinical SEEGUnit Matching Accuracy: 0.0792 -> 0.6596Improved
add set-based semantic decomposer (ablation)BrainMosaic · ChiscoUnit Matching Accuracy: 0.0260 -> 0.5617Improved
decode into continuous semantic space instead of multi-label classification (ablation)BrainMosaic · ChiscoUnit Matching Accuracy: 0.0044 -> 0.5617Improved
add LLM semantic decoder for sentence reconstruction (ablation)BrainMosaic · Clinical SEEGSentence Reconstruction Similarity: 0.5456 -> 0.6651Improved
add LLM semantic decoder for sentence reconstruction (ablation)BrainMosaic · ChiscoSentence Reconstruction Similarity: 0.5133 -> 0.6206Improved
set matching instead of LSTM sequential decoding of unitsBrainMosaic · ChiscoUnit Matching Accuracy: 0.0301 -> 0.5617Improved
constrain generation with decoded semantic units vs end-to-end Neuro2SemanticBrainMosaic · ZuCoSRSentence Reconstruction Similarity: 0.5211 -> 0.6982Improved
expand retrieval vocabulary with up to 30000 unseen words (ablation)BrainMosaic · Clinical SEEGUnit Matching Accuracy: 0.6596 -> 0.5944 (MUS 0.8124 -> 0.8042)Mixed
increase training data ratio from 0.1 to 1.0 (ablation)BrainMosaic · Clinical SEEG (Base+30000 vocabulary)Unit Matching Accuracy: 0.3439 -> 0.5944Improved

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