# MIRAGE: Robust multi-modal architectures translate fMRI-to-image models from vision to mental imagery

arXiv: https://arxiv.org/abs/2605.17198 · HTML: https://mlsanity.com/paper/2605.17198/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 76 references that are in the map.
- First posted on arXiv 16 May 2026.

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)
- [Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images](https://mlsanity.com/paper/2011.10650/) (2020)
- [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://mlsanity.com/paper/2211.08332/) (2022)
- [Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors](https://mlsanity.com/paper/2305.18274/) (2023)
- [Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding](https://mlsanity.com/paper/2211.06956/) (2022)
- [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)
- [MindBridge: A Cross-Subject Brain Decoding Framework](https://mlsanity.com/paper/2404.07850/) (2024)
- [UniBrain: Unify Image Reconstruction and Captioning All in One Diffusion Model from Human Brain Activity](https://mlsanity.com/paper/2308.07428/) (2023)
- [Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities](https://mlsanity.com/paper/2305.17214/) (2023)
- [Brain Captioning: Decoding human brain activity into images and text](https://mlsanity.com/paper/2305.11560/) (2023)
- [NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation](https://mlsanity.com/paper/2403.18211/) (2024)
- [Improving visual image reconstruction from human brain activity using latent diffusion models via multiple decoded inputs](https://mlsanity.com/paper/2306.11536/) (2023)
- [Through their eyes: multi-subject Brain Decoding with simple alignment techniques](https://mlsanity.com/paper/2309.00627/) (2023)
- [Spurious reconstruction from brain activity](https://mlsanity.com/paper/2405.10078/) (2024)
- [Reconstructing seen images from human brain activity via guided stochastic search](https://mlsanity.com/paper/2305.00556/) (2023)
- [Brain-optimized inference improves reconstructions of fMRI brain activity](https://mlsanity.com/paper/2312.07705/) (2023)
- [NSD-Imagery: A benchmark dataset for extending fMRI vision decoding methods to mental imagery](https://mlsanity.com/paper/2506.06898/) (2025)
- [Second Sight: Using brain-optimized encoding models to align image distributions with human brain activity](https://mlsanity.com/paper/2306.00927/) (2023)

## Abstract (arXiv)

To be useful for downstream applications, vision decoding models that are trained to reconstruct seen images from human brain activity must be able to generalize to internally generated visual representations, i.e., mental images. In an analysis of the recently released NSD-Imagery dataset, we demonstrated that while some modern vision decoders can perform quite well on mental image reconstruction, some fail, and that state-of-the-art (SOTA) performance on seen image reconstruction is no guarantee of SOTA performance on mental image reconstruction. Motivated by these findings, we developed MIRAGE, a method explicitly designed to train on vision datasets and cross-decode mental images from brain activity. MIRAGE employs a linear backbone and multi-modal text and image features as input to a diffusion model. Feature metrics and human raters establish MIRAGE as SOTA for mental image reconstruction on the NSD-Imagery benchmark. With ablation analysis we show that mental image reconstruction works best when decoders use image features with relatively few dimensions and include guidance from text-based and both high- and low-level image-based features. Our work indicates that--given the right architecture--existing large-scale datasets using external stimuli are viable training data for decoding mental images, and warrant optimism about the future success and utility of mental image reconstruction.