Research map / Vision-language and multimodal / Human and embodied modeling
Meta-Learning In-Context Enables Training-Free Cross Subject Brain Decoding
Mu Nan, Muquan Yu, Weijian Mai, Jacob S. Prince, Hossein Adeli, Rui Zhang, Jiahang Cao, Benjamin Becker, John A. Pyles, Margaret M. Henderson, Chunfeng Song, Nikolaus Kriegeskorte and 3 more
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add in-context real-data trained BrainCoDec instead of synthetic pretraining only (ablation) | BrainCoDec-200 · NSD S1 | top-1 accuracy: 3.67 -> 25.5 | Improved |
| use in-context model instead of gradient-based functional inversion (ablation) | BrainCoDec-200 · NSD S1 | top-1 accuracy: 1.61 -> 25.5 | Improved |
| add real-data finetuning to synthetic pretraining (ablation) | BrainCoDec-200 · NSD S1 | cosine similarity: 0.23 -> 0.81 | Improved |
| train with subject holdout vs without (seen subject) (ablation) | BrainCoDec-200 · NSD S1 | top-1 accuracy: 25.5 -> 28.3 | No clear effect |
| train with subject holdout vs without (seen subject) (ablation) | BrainCoDec-200 · NSD S1 | top-5 accuracy: 56.6 -> 61.1 | No clear effect |
| replace MindEye2 with BrainCoDec-200 on unseen subjects | MindEye2 · NSD mean over S1,S2,S5,S7 | top-1 accuracy: 3.90% -> 22.7% | Improved |
| replace TGBD with BrainCoDec-200 on unseen subjects | TGBD · NSD mean over S1,S2,S5,S7 | top-5 accuracy: 3.09% -> 54.0% | Improved |
| use CLIP instead of DINOv2 image backbone | BrainCoDec · BOLD5000 | top-1 accuracy: 13.99 -> 31.45 | Improved |
| use CLIP instead of SigLIP image backbone | BrainCoDec · BOLD5000 | top-1 accuracy: 23.67 -> 31.45 | Improved |
| increase image context or voxel context size | BrainCoDec · NSD | retrieval accuracy | Improved |
| mask category-selective ROI voxels (faces, food, words) (ablation) | BrainCoDec · NSD unseen subjects | cosine similarity | No clear effect |
| mask scene-selective regions (PPA/OPA/RSC) (ablation) | BrainCoDec · NSD unseen subjects | cosine similarity | Hurt |
Closest papers by meaning
- See Through Their Minds: Learning Transferable Brain Decoding Models from Cross-Subject fMRI (AAAI 2025 · similarity 0.93)
- Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex (NeurIPS 2025 · similarity 0.92)
- Toward Generalizing Visual Brain Decoding to Unseen Subjects (ICLR 2025 · similarity 0.91)
- $i$MIND: Insightful Multi-subject Invariant Neural Decoding (NeurIPS 2025 · similarity 0.91)
- MindBridge: A Cross-Subject Brain Decoding Framework (CVPR 2024 · similarity 0.91)
- Brain decoding: toward real-time reconstruction of visual perception (ICLR 2024 · similarity 0.90)
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.
