AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

BrainCoT: A Multi-Task Zero-Shot Brain Signal Foundation Model with Neurometric-Anchored Chain-of-Thought Reasoning

Yiyu Gui, Mingzhi Chen, Guibo Luo, Yuchao Yang

NeurIPS 2026 · Large language models › Language, safety and interpretability · approach: Faithfulness of LLM explanations · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes BrainCoT, a multi-task zero-shot brain signal foundation model that uses neurometric-anchored chain-of-thought reasoning to generalize across tasks and subjects without target-specific supervised adaptation.

Problem

Brain signal models struggle to generalize across multi-center heterogeneity, inter-subject variability, and diverse tasks, and existing brain foundation models still require target-data-specific supervised adaptation.

Approach

Combines a brain signal foundation model with chain-of-thought reasoning anchored to neurometrics so that it can perform multiple tasks zero-shot without target-specific supervised fine-tuning.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
generate neurometric-anchored reasoning instead of answering directly (ablation)BrainCoT stage-II · 12 datasets zero-shotACC / AUC: 62.91 -> 67.41 ACC; 69.56 -> 74.33 AUCImproved
add stage-II reasoning pretraining (direct mode) (ablation)BrainCoT · 12 datasets zero-shotACC / AUC: 57.59 -> 62.91 ACC; 63.18 -> 69.56 AUCImproved
corrupt reasoning trajectory by randomly replacing neurometric names and intensities (ablation)BrainCoT reasoning · 12 datasets zero-shotACC / AUC: 67.41 -> 60.71 ACC; 74.33 -> 67.96 AUCHurt
add Decision-Consistent Reasoning (DCR) training (ablation)BrainCoT · 12 datasets zero-shotaccuracyImproved
add MoE backbone (ablation)BrainCoT · 12 datasets zero-shotaccuracyImproved
use MI-weighted evidence sampling instead of random features (ablation)BrainCoT · 12 datasets zero-shotaccuracyImproved
scale model from Small (83.8M) to Base (329.2M) (ablation)BrainCoT · zero-shotACC / AUCImproved
zero-shot BrainCoT versus 1% linear probing baselinesBrainCoT · 12 datasetsACC / AUC: 63.56 -> 67.41 ACC; 68.36 -> 74.33 AUC (strongest baselines)Improved
compare BrainCoT zero-shot with 10% linear probing baselinesBrainCoT · 12 datasetsACC: 67.41 vs 67.69 (BrainBERT)Mixed
use BrainCoT instead of baselines under full fine-tuningBrainCoT · 12 datasetsAUC: 85.01 vs 85.95 (ELM-MIL)No clear effect

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