# NeuroSwift: A Lightweight Cross-Subject Framework for fMRI Visual Reconstruction of Complex Scenes

arXiv: https://arxiv.org/abs/2510.02266 · HTML: https://mlsanity.com/paper/2510.02266/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 52 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors](https://mlsanity.com/paper/2305.18274/) (2023)
- [Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models](https://mlsanity.com/paper/2304.12526/) (2023)
- [Generic decoding of seen and imagined objects using hierarchical visual features](https://mlsanity.com/paper/1510.06479/) (2015)
- [MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data](https://mlsanity.com/paper/2403.11207/) (2024)
- [Natural scene reconstruction from fMRI signals using generative latent diffusion](https://mlsanity.com/paper/2303.05334/) (2023)
- [Mind Reader: Reconstructing complex images from brain activities](https://mlsanity.com/paper/2210.01769/) (2022)
- [MindBridge: A Cross-Subject Brain Decoding Framework](https://mlsanity.com/paper/2404.07850/) (2024)
- [BOLD5000: A public fMRI dataset of 5000 images](https://mlsanity.com/paper/1809.01281/) (2018)
- [Decoding natural image stimuli from fMRI data with a surface-based convolutional network](https://mlsanity.com/paper/2212.02409/) (2022)
- [MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural Diffusion](https://mlsanity.com/paper/2308.04249/) (2023)
- [Reconstructing Natural Scenes from fMRI Patterns using BigBiGAN](https://mlsanity.com/paper/2001.11761/) (2020)
- [DREAM: Visual Decoding from Reversing Human Visual System](https://mlsanity.com/paper/2310.02265/) (2023)
- [Reconstructing Faces from fMRI Patterns using Deep Generative Neural Networks](https://mlsanity.com/paper/1810.03856/) (2018)
- [UniBrain: Unify Image Reconstruction and Captioning All in One Diffusion Model from Human Brain Activity](https://mlsanity.com/paper/2308.07428/) (2023)
- [BrainCLIP: Bridging Brain and Visual-Linguistic Representation Via CLIP for Generic Natural Visual Stimulus Decoding](https://mlsanity.com/paper/2302.12971/) (2023)
- [NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation](https://mlsanity.com/paper/2403.18211/) (2024)
- [Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GAN](https://mlsanity.com/paper/2101.12083/) (2021)
- [MindTuner: Cross-Subject Visual Decoding with Visual Fingerprint and Semantic Correction](https://mlsanity.com/paper/2404.12630/) (2024)
- [BrainGuard: Privacy-Preserving Multisubject Image Reconstructions from Brain Activities](https://mlsanity.com/paper/2501.14309/) (2025)

## Abstract (arXiv)

Reconstructing visual information from brain activity via computer vision technology provides an intuitive understanding of visual neural mechanisms. Despite progress in decoding fMRI data with generative models, achieving accurate cross-subject reconstruction of visual stimuli remains challenging and computationally demanding. This difficulty arises from inter-subject variability in neural representations and the brain's abstract encoding of core semantic features in complex visual inputs. To address these challenges, we propose NeuroSwift, which integrates complementary adapters via diffusion: AutoKL for low-level features and CLIP for semantics. NeuroSwift's CLIP Adapter is trained on Stable Diffusion generated images paired with COCO captions to emulate higher visual cortex encoding. For cross-subject generalization, we pretrain on one subject and then fine-tune only 17 percent of parameters (fully connected layers) for new subjects, while freezing other components. This enables state-of-the-art performance with only one hour of training per subject on lightweight GPUs (three RTX 4090), and it outperforms existing methods.