OmniMouse: Scaling properties of multi-modal, multi-task Brain Models on 150B Neural Tokens

2026-04-20

AI Summary

This study investigates whether scaling laws established in artificial intelligence—governing the relationship between data, model size, and performance—extend to modeling brain activity, particularly in multimodal, multitask neural prediction settings. Leveraging a large-scale dataset comprising 150 billion neural tokens from the mouse visual cortex, we introduce OmniMouse, a unified model capable of flexibly combining diverse tasks such as neural response prediction and behavioral decoding. Systematic analysis reveals, for the first time, that brain model performance scales robustly with data volume but saturates with increasing parameter count, challenging the dominant AI paradigm that prioritizes parameter scaling. This finding suggests the potential existence of phase transitions or emergent capabilities in neural modeling. OmniMouse consistently outperforms task-specific baselines across nearly all benchmarks, underscoring the pivotal role of data-driven approaches in computational neuroscience.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multimodal Learning
• Humans and AI: Brain-Sensing and Analysis

Application Category

• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Scaling data and artificial neural networks has transformed AI, driving breakthroughs in language and vision. Whether similar principles apply to modeling brain activity remains unclear. Here we leveraged a dataset of 3.1 million neurons from the visual cortex of 73 mice across 323 sessions, totaling more than 150 billion neural tokens recorded during natural movies, images and parametric stimuli, and behavior. We train multi-modal, multi-task models that support three regimes flexibly at test time: neural prediction, behavioral decoding, neural forecasting, or any combination of the three. OmniMouse achieves state-of-the-art performance, outperforming specialized baselines across nearly all evaluation regimes. We find that performance scales reliably with more data, but gains from increasing model size saturate. This inverts the standard AI scaling story: in language and computer vision, massive datasets make parameter scaling the primary driver of progress, whereas in brain modeling -- even in the mouse visual cortex, a relatively simple system -- models remain data-limited despite vast recordings. The observation of systematic scaling raises the possibility of phase transitions in neural modeling, where larger and richer datasets might unlock qualitatively new capabilities, paralleling the emergent properties seen in large language models. Code available at https://github.com/enigma-brain/omnimouse.

Problem

• brain modeling
• scaling laws
• neural data
• multi-modal learning
• model generalization

Innovation

• neural scaling
• multi-modal brain modeling
• data-limited regime
• emergent capabilities
• OmniMouse