Research map / Image generation / Fast diffusion sampling
Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer
Roman Beliy, Amit Zalcher, Jonathan Kogman, navve wasserman, michal Irani
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 ~120k external images with predicted fMRI (ablation) | Brain-IT · NSD | PixCorr: 0.365 -> 0.386 | Improved |
| add external images (ablation) | Brain-IT · NSD | SSIM: 0.494 -> 0.486 | Hurt |
| functional clustering instead of anatomical clustering (ablation) | Brain-IT · NSD | PixCorr: 0.378 -> 0.386 | Improved |
| increase cluster count from 8 to 128 (ablation) | Brain-IT · NSD | Eff: 0.588 -> 0.564 | Improved |
| increase cluster count from 128 to 512 (ablation) | Brain-IT · NSD | PixCorr: 0.386 -> 0.392 | No clear effect |
| add low-level DIP branch to semantic branch (ablation) | Brain-IT · NSD | PixCorr: 0.336 -> 0.386 | Improved |
| add semantic branch to low-level branch (ablation) | Brain-IT · NSD | CLIP: 85.8 -> 96.4 | Improved |
| use BIT instead of MLP for low-level features (ablation) | low-level branch · NSD subject 1 | PixCorr: 0.267 -> 0.500 | Improved |
| Brain-IT with 1 hour vs MindTuner 1 hour | Brain-IT · NSD | PixCorr: 0.224 -> 0.331 | Improved |
| reduce subject-specific data from 1 hour to 15 minutes | Brain-IT · NSD subject 1 | PixCorr: 0.396 -> 0.336 | Hurt |
| Brain-IT vs NeuroVLA on CLIP two-way | Brain-IT · NSD | CLIP: 97.5 vs 96.4 | Hurt |
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.
- MindEye2 — MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data (ICML 2024) · better on 4 of 4 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
- MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding (NeurIPS 2025 · similarity 0.89)
- Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction (NeurIPS 2024 · similarity 0.89)
- MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data (ICML 2024 · similarity 0.89)
- See Through Their Minds: Learning Transferable Brain Decoding Models from Cross-Subject fMRI (AAAI 2025 · similarity 0.89)
- MindBridge: A Cross-Subject Brain Decoding Framework (CVPR 2024 · similarity 0.88)
- Brain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEG (NeurIPS 2026 · similarity 0.87)
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.
