# BrainBits: How Much of the Brain are Generative Reconstruction Methods Using?

arXiv: https://arxiv.org/abs/2411.02783 · HTML: https://mlsanity.com/paper/2411.02783/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 5 Nov 2024.

## Builds on (most cited first, 22 of 22)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [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)
- [Generic decoding of seen and imagined objects using hierarchical visual features](https://mlsanity.com/paper/1510.06479/) (2015)
- [Natural scene reconstruction from fMRI signals using generative latent diffusion](https://mlsanity.com/paper/2303.05334/) (2023)
- [Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity](https://mlsanity.com/paper/2305.11675/) (2023)
- [Reconstruction of Perceived Images from fMRI Patterns and Semantic Brain Exploration using Instance-Conditioned GANs](https://mlsanity.com/paper/2202.12692/) (2022)
- [DREAM: Visual Decoding from Reversing Human Visual System](https://mlsanity.com/paper/2310.02265/) (2023)
- [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)
- [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)
- [Aligning brain functions boosts the decoding of visual semantics in novel subjects](https://mlsanity.com/paper/2312.06467/) (2023)

## Built on by (most cited first, 5 of 5)

- [MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding](https://mlsanity.com/paper/2505.15946/) (2025)
- [Learning Interpretable Representations Leads to Semantically Faithful EEG-to-Text Generation](https://mlsanity.com/paper/2505.17099/) (2025)
- [Towards Interpretable Visual Decoding with Attention to Brain Representations](https://mlsanity.com/paper/2509.23566/) (2025)
- [MIRAGE: Robust multi-modal architectures translate fMRI-to-image models from vision to mental imagery](https://mlsanity.com/paper/2605.17198/) (2026)
- [Lost in Visual Translation: A VLM-Assisted Perceptual-Semantic Coherence Framework for EEG-to-Image Reconstruction](https://mlsanity.com/paper/2607.12364/) (2026)

## Abstract (arXiv)

When evaluating stimuli reconstruction results it is tempting to assume that higher fidelity text and image generation is due to an improved understanding of the brain or more powerful signal extraction from neural recordings. However, in practice, new reconstruction methods could improve performance for at least three other reasons: learning more about the distribution of stimuli, becoming better at reconstructing text or images in general, or exploiting weaknesses in current image and/or text evaluation metrics. Here we disentangle how much of the reconstruction is due to these other factors vs. productively using the neural recordings. We introduce BrainBits, a method that uses a bottleneck to quantify the amount of signal extracted from neural recordings that is actually necessary to reproduce a method's reconstruction fidelity. We find that it takes surprisingly little information from the brain to produce reconstructions with high fidelity. In these cases, it is clear that the priors of the methods' generative models are so powerful that the outputs they produce extrapolate far beyond the neural signal they decode. Given that reconstructing stimuli can be improved independently by either improving signal extraction from the brain or by building more powerful generative models, improving the latter may fool us into thinking we are improving the former. We propose that methods should report a method-specific random baseline, a reconstruction ceiling, and a curve of performance as a function of bottleneck size, with the ultimate goal of using more of the neural recordings.