Meta's TRIBE v2: Tri-modal foundation model predicts human brain activity from 1,000+ hours of fMRI
burny_tech · x · 2026-09-28
Stéphane d'Ascoli, Jean-Rémi King and colleagues at Meta introduced TRIBE v2, a tri-modal (video, audio, language) foundation model that predicts human brain activity across naturalistic and experimental conditions.
- Unified training on 1,000+ hours of fMRI from 720 subjects
- Several-fold accuracy improvements over traditional linear encoding models on novel stimuli, tasks and subjects
- Enables in silico experimentation: reproduces decades of established results in classic visual and neuro-linguistic paradigms
- Interpretable latent features reveal fine-grained topography of multisensory integration
Paper: arXiv:2605.04326.
More from AGI Musings
- AI growth debate: Hanania predicts just 3.5% GDP bump in five years, drawing fire — QuintinPope5 · 2026-09-28
- Coder's take: three realistic paths for programmers facing the AI disruption — sven_ai · 2026-09-28
- Stop calling AI failures 'rogue' — they're foreseeable harms, argues Sigal Samuel — mmitchell_ai · 2026-09-28
- Blogger predicts all major US AGI labs will reach AGI in 2027, then ASI — Dr_Singularity · 2026-09-28
- Wait But Why's 2015 AI Revolution essay reads even more relevant 11 years later — louisvarge · 2026-09-28
- AI May Replace Tasks Without Replacing Your Job — kevinsurace · 2026-09-28