Alignment between Brains and AI: Evidence for Convergent Evolution across Modalities, Scales and Training Trajectories

TL;DR

This study shows that high-performing AI models develop brain-like representations similar to biological systems, with alignment patterns evolving during training and across different modalities, revealing convergent evolution in computation.

Contribution

It provides large-scale evidence that AI models naturally develop brain-like representations during training, highlighting convergent evolution across modalities and layers, and linking alignment to performance.

Findings

Higher-performing models show stronger brain alignment.

Language models align more strongly with brain regions than vision models.

Alignment increases during training and precedes performance improvements.

Abstract

Artificial and biological systems may evolve similar computational solutions despite fundamental differences in architecture and learning mechanisms -- a form of convergent evolution. We demonstrate this phenomenon through large-scale analysis of alignment between human brain activity and internal representations of over 600 AI models spanning language and vision domains, from 1.33M to 72B parameters. Analyzing 60 million alignment measurements reveals that higher-performing models spontaneously develop stronger brain alignment without explicit neural constraints, with language models showing markedly stronger correlation (r=0.89, p<7.5e-13) than vision models (r=0.53, p<2.0e-44). Crucially, longitudinal analysis demonstrates that brain alignment consistently precedes performance improvements during training, suggesting that developing brain-like representations may be a necessary stepping stone toward higher capabilities. We find systematic patterns: language models exhibit strongest alignment with limbic and integrative regions, while vision models show progressive alignment with visual cortices; deeper processing layers converge across modalities; and as representational scale increases, alignment systematically shifts from primary sensory to higher-order associative regions. These findings provide compelling evidence that optimization for task performance naturally drives AI systems toward brain-like computational strategies, offering both fundamental insights into principles of intelligent information processing and practical guidance for developing more capable AI systems.