Author

Tikun Ông

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Inherent Trade-offs when Enforcing Correct Data Symmetries in Multi-head Self-attention

We give a complete characterization of equivariant multi-head self-attention (MHSA): if an MHSA layer is equivariant to a symmetry group $G$, then $G$ can only act by permuting head-clusters, with QK and OV matrices satisfying an equivariance constraint tied to the group action. As a consequence, we prove that any fixe...

Tikun Ông, Georg Bökman · 0 citations

#machine learning Preprint Aug 2026

No Equivariant Architecture Covers All Equivariant Attention

It is proved that any fixed MHSA architecture that achieves exact equivariance by polynomially parameterizing unconstrained MHSA parameters inevitably leads to expressivity loss within the class of equivariant maps.

Tikun Ông · 0 citations