ENIGMA decodes images from EEG with <1% params of priors, achieving SOTA on THINGS-EEG2 and consumer benchmarks. Fine-tunes on new subjects in 15 minutes using simple spatio-temporal backbone and latent alignment. Includes behavioral human evaluations.
Key Points
- 1.Works on research and consumer EEG
- 2.Rapid subject fine-tuning efficiency
- 3.Standardized fMRI-like metrics
Impact Analysis
Pushes practical BCI toward real-world deployability on low resources.
Technical Details
Multi-subject backbone + MLP projector to visual latents; extensive ablations.