SOURCE-LINKED INTELLIGENCE

Conditioned Initialization for Attention

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Transformers are a dominant architecture in modern machine learning, powering applications across vision, language, and beyond. At the core of their success lies the attention layer, where the query, key, and value matrices determine how token dependencies are captured. While considerable work has focused on scaling and optimizing Transformers, comparatively little attention has been paid to how the weights of the queries, keys and values are initialized. Common practice relies on random initialization or alternatives such as mimetic initialization, which imitates weight patterns from converge

Read original source ↗ Open in workspace

recordType

paper

region

Global