Today we're introducing TRIBE v2 (Trimodal Brain Encoder), a foundation model trained to predict how the human brain responds to almost any sight or sound. Building on our Algonauts 2025 award-winning architecture, TRIBE v2 draws on 500+ hours of fMR - x.com

2026-03-26 · Source: https://x.com/aiatmeta via Google News · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Computational Neuroscience · Depth: Expert, quick

Summary

Meta has introduced TRIBE v2 (Trimodal Brain Encoder), a foundation model designed to predict human brain responses to visual and auditory stimuli. This model builds upon an Algonauts 2025 award-winning architecture, utilizing over 500 hours of fMRI recordings collected from more than 700 individuals. TRIBE v2 aims to create a digital twin of neural activity, enabling zero-shot predictions for new subjects, languages, and tasks without requiring prior training data for those specific conditions. A public demo is available for users to explore its capabilities.

Key takeaway

For AI Scientists and Research Scientists developing brain-computer interfaces or neural decoding systems, TRIBE v2 offers a significant advancement in modeling human brain responses. Its zero-shot prediction capabilities across diverse subjects and tasks suggest a path toward more generalized and adaptable neural models. You should investigate its architecture and performance for potential integration or inspiration in your own research, particularly for applications requiring robust generalization.

Key insights

TRIBE v2 is a foundation model predicting brain responses to sights and sounds using fMRI data.

Principles

• Zero-shot prediction extends model utility.
• Large-scale fMRI data enables neural activity modeling.

Method

TRIBE v2 was trained on 500+ hours of fMRI data from 700+ people to predict neural activity, enabling zero-shot generalization across subjects, languages, and tasks.

In practice

• Explore the TRIBE v2 demo.
• Consider fMRI for neural activity mapping.

Topics

• TRIBE v2
• Trimodal Brain Encoder
• Foundation Models
• fMRI Recordings
• Neural Activity Prediction

Best for: AI Scientist, Research Scientist

Related on AIssential

• Introducing TRIBE v2: A Predictive Foundation Model Trained to Understand How the Human Brain Processes Complex Stimuli - AI at Meta — TRIBE v2 is a foundation model predicting high-resolution human brain activity from diverse sensory stimuli.
• Boosting Brain-to-Image Decoding with TRIBE v2 Data Augmentation — Synthetic fMRI data from TRIBE v2 significantly boosts brain-to-image decoding accuracy, enabling zero-shot capabilities.
• A foundation model of vision, audition, and language for in-silico neuroscience — TRIBE v2 unifies vision, audition, and language to predict human brain activity, enabling in silico neuroscience.
• A foundation model of vision, audition, and language for in-silico neuroscience | Research - AI at Meta — TRIBE v2 unifies cognitive neuroscience by predicting human brain activity across diverse conditions using a tri-modal foundation model.
• Boosting Brain-to-Image Decoding with TRIBE v2 Data Augmentation — Synthetic fMRI data from pretrained models like TRIBE v2 can significantly boost brain-to-image decoding in low-data regimes.
• Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete Diffusion — Mind-Omni unifies brain-vision-language tasks via discrete diffusion and a Brain Tokenizer for multi-modal interaction.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by https://x.com/aiatmeta via Google News.