SOURCE-LINKED INTELLIGENCE

Why shared attention vectors fail: a case for outcome-indexed tuning

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Dimensional attention in learning is often implemented as a globally shared attention vector, where each stimulus dimension corresponds to a single scalar. These scalars are learned by models through gradient-descent on error, where predictive features acquire more salience. We show that under multi-outcome learning, where models predict more than one outcome, this shared vector becomes unstable; it collapses to its bounds and prevents the models from learning meaningful attentional tunings for learning and generalization. We address this by introducing an outcome-indexed attentional matrix th

Read original source ↗ Open in workspace

recordType

paper

region

Global