Introducing TRIBE v2: A Predictive Foundation Model Trained to Understand How the Human Brain Processes Complex Stimuli - AI at Meta

2026-03-26 · Source: ai.meta.com via Google News · Field: Science & Research — Life Sciences & Biology, Health & Medical Research · Depth: Expert, quick

Summary

Meta AI has introduced TRIBE v2, a predictive foundation model designed to act as a digital twin of human neural activity. This next-generation model offers significantly improved speed, accuracy, and a 70x resolution increase compared to previous models, enabling predictions of how the brain responds to various sights and sounds. TRIBE v2 was trained on a large dataset from over 700 healthy volunteers exposed to diverse media, including images, podcasts, videos, and text. It reliably predicts high-resolution fMRI brain activity, supporting zero-shot predictions for new subjects, languages, and tasks, and consistently outperforms standard modeling approaches. The model, codebase, research paper, and an interactive demo are being released to the public.

Key takeaway

For neuroscientists and clinical researchers developing new hypotheses, TRIBE v2 offers a powerful computational simulation tool to rapidly test theories of brain function. You can leverage its 70x resolution increase and zero-shot prediction capabilities to explore complex stimuli responses, potentially accelerating breakthroughs in understanding and treating neurological conditions without requiring extensive human subject trials.

Key insights

TRIBE v2 is a foundation model predicting high-resolution human brain activity from diverse sensory stimuli.

Principles

• Digital twins accelerate neuroscience research.
• Large datasets improve brain activity prediction.

Method

TRIBE v2 was trained on fMRI data from over 700 volunteers exposed to images, podcasts, videos, and text to predict high-resolution brain activity, enabling zero-shot generalization.

In practice

• Test neuroscience theories without human subjects.
• Guide AI development with neuroscientific principles.
• Accelerate neurological disorder treatment research.

Topics

• TRIBE v2
• Foundation Model
• Human Brain Simulation
• fMRI Prediction
• Neuroscience Research

Code references

• facebookresearch/tribev2

Best for: Research Scientist, AI Scientist

Related on AIssential

• 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.
• 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 — TRIBE v2 is a foundation model predicting brain responses to sights and sounds using fMRI data.
• 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.
• 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.
• 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.
• 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 ai.meta.com via Google News.