← Back to all articles
arXiv cs.AIOctober 7, 2026

SO(3)-RoPE for Spherical Transformers

Excerpt

arXiv:2610.06229v1 Announce Type: cross Abstract: Spherical data arise in many scientific applications. Often spherical transformers disregard the geometry of the underlying spherical domain, causing distortions and coordinate singularities near the poles. We introduce SO(3)-RoPE, a relative positional embedding that incorporates spherical geometry into transformer attention through unitary SO(3) representations. Our formulation is SO(3)-equivariant and compatible with FlashAttention, retaining