Alljoined 1.6M
2025
We introduce the largest public dataset for EEG-image decoding: 4 hours of recordings per participant across 20 subjects, collected using consumer-grade hardware. We model neural scaling laws and demonstrate log-linear scaling.
Alljoined is creating a future where people can better understand themselves and connect with technology.
Our advanced AI models extract semantic content and thought patterns from brain signals
Using large-scale EEG datasets and cutting edge ML research, we’re building models that decode images, emotion, and eventually complex cognitive processes.
Our research is broad: spanning from semantic understanding and abstract reasoning to inner speech and intentional planning.
Alljoined pushes the frontier of neural decoding with leading peer-reviewed papers
Open paper
MindEye2
2024
MindEye2 introduces a multi-subject fMRI-to-image architecture that trains 40× faster than previous state-of-the-art while matching performance. Accepted to ICML.
NSD-Imagery
2025
The first and only dataset for complex mental imagery reconstruction from fMRI. Accepted to CVPR (Highlight paper).
Compare Image Reconstructions
Using solely evoked EEG responses, our models reconstruct the original stimulus, leading performance across various datasets.
1
Original
2
Our Reconstruction
3
Li et. al, 2024
4
Fei et. al, 2024
1
Original
2
Our Reconstruction
3
Li et. al, 2024
4
Fei et. al, 2024
1
Original
2
Our Reconstruction
3
Li et. al, 2024
4
Fei et. al, 2024
1
Original
2
Our Reconstruction
3
Li et. al, 2024
4
Fei et. al, 2024
1
Original
2
Our Reconstruction
3
Li et. al, 2024
4
Fei et. al, 2024
1
Original
2
Our Reconstruction
3
Li et. al, 2024
4
Fei et. al, 2024Our goal is to map out the full space of human consciousness
Study Participant
San Francisco
Computational Neuroscientist
San Francisco
Machine Learning Researcher
San Francisco
Research Intern (Fall)
San Francisco