Contravariance Theory: Strong Alignment for Minimal Solutions to Hard Tasks
A series of results from the NeuroAI over the past fifteen years have raised core questions both about how to compare Deep Neural Network (DNN) models to the brain, and about how much convergent evolution to expect between artificial networks and real brain networks. Here, we show that for any two minimal DNN solutions to a sufficiently hard task: (i) "weak" alignment of network representations based on affine mappings guarantees "strong" alignment of privileged axes, and (ii) alignment "zippers" up the network hierarchy, causing the emergence of privileged axes from end-to-end task optimizati
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 49%A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models - Apple Machine Learning Research →
- PossiblePossibly related (embedding) · 47%sonos/tract →
- PossiblePossibly related (embedding) · 46%nilearn/nilearn →
- LinkedLinked via arxiv author · 85%Dan Yamins →
“Contravariance Theory: Strong Alignment for Minimal Solutions to Hard Tasks”
- LinkedLinked via arxiv author · 85%Aran Nayebi →
“Contravariance Theory: Strong Alignment for Minimal Solutions to Hard Tasks”