arXiv:2604.18827v2 Announce Type: replace-cross 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 decodin
This research builds on recent breakthroughs in scaling AI models by applying similar principles to complex biological data, particularly brain activity.
Understanding the scaling properties of brain models could lead to significant advancements in AI, neuroscience, and the development of more sophisticated AI agents.
The ability to model neural activity multi-modally opens new avenues for AI development, potentially bridging the gap between biological and artificial intelligence.
- · AI researchers
- · Neuroscience companies
- · Biotech sector
- · Pharmaceutical R&D
- · Traditional AI development paradigms relying solely on synthetic datasets
- · Research groups without access to large-scale biological data
This research could lead to more biologically inspired AI architectures.
Improved brain models could accelerate development in neural prosthetics and therapeutic interventions for neurological disorders.
A deeper understanding of brain scaling might inform the creation of truly general artificial intelligence by mimicking biological intelligence more closely.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI