# UniBrain: A Unified Model for Cross-Subject Brain Decoding

arXiv: https://arxiv.org/abs/2412.19487 · HTML: https://mlsanity.com/paper/2412.19487/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Dec 2024.

## Built on by (most cited first, 11 of 11)

- [MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-Text Decoding](https://mlsanity.com/paper/2502.15786/) (2025)
- [Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer](https://mlsanity.com/paper/2510.25976/) (2025)
- [Multigranular Evaluation for Brain Visual Decoding](https://mlsanity.com/paper/2507.07993/) (2025)
- [SemVideo: Reconstructs What You Watch from Brain Activity via Hierarchical Semantic Guidance](https://mlsanity.com/paper/2602.21819/) (2026)
- [FPED: A Functional-Network Prior-Guided Mixture-of-Experts Framework for Interpretable Brain Decoding](https://mlsanity.com/paper/2605.19279/) (2026)
- [SEED: Towards More Accurate Semantic Evaluation for Visual Brain Decoding](https://mlsanity.com/paper/2503.06437/) (2025)
- [Unified Multimodal Brain Decoding via Cross-Subject Soft-ROI Fusion](https://mlsanity.com/paper/2512.20249/) (2025)
- [The Pictorial Cortex: Zero-Shot Cross-Subject fMRI-to-Image Reconstruction via Compositional Latent Modeling](https://mlsanity.com/paper/2601.15071/) (2026)
- [StableMind: Source-Free Cross-Subject fMRI Decoding with Regularized Adaptation](https://mlsanity.com/paper/2605.02586/) (2026)
- [Brain-IT-VQA: From Brain Signals to Answers](https://mlsanity.com/paper/2605.29588/) (2026)
- [Task-guided cross-subject latent alignment: a multi-encoder-decoder VAE](https://mlsanity.com/paper/2606.15989/) (2026)

## Abstract (arXiv)

Brain decoding aims to reconstruct original stimuli from fMRI signals, providing insights into interpreting mental content. Current approaches rely heavily on subject-specific models due to the complex brain processing mechanisms and the variations in fMRI signals across individuals. Therefore, these methods greatly limit the generalization of models and fail to capture cross-subject commonalities. To address this, we present UniBrain, a unified brain decoding model that requires no subject-specific parameters. Our approach includes a group-based extractor to handle variable fMRI signal lengths, a mutual assistance embedder to capture cross-subject commonalities, and a bilevel feature alignment scheme for extracting subject-invariant features. We validate our UniBrain on the brain decoding benchmark, achieving comparable performance to current state-of-the-art subject-specific models with extremely fewer parameters. We also propose a generalization benchmark to encourage the community to emphasize cross-subject commonalities for more general brain decoding. Our code is available at https://github.com/xiaoyao3302/UniBrain.