← Search

Hariprasath Govindarajan

2 accepted papers

2026

QUEST: A robust attention formulation using query-modulated spherical attention

ICLR 2026poster

The Transformer model architecture has become one of the most widely used in deep learning and the attention mechanism is at its core. The standard attention formulation uses a softmax operation applied to a scaled dot product between query and key vectors. We explore the role played by norms of the…

Cited by 0SourcecodeScholar