Congratulations to Hao for his ICML Oral on rotationally equivariant transformers: tum-pbs.github.io/revit-web/ 👍 The key idea is to transform physical fields into local canonical coordinate systems, enabling standard self-attention while preserving physical symmetries
Who's Who of AI
thuereygroup.bsky.social
Professor @ TUM | Making numerical methods and deep learning play nicely together | Fluids | Computer Graphics
What they're sharing
ReViT: Rotational-equivariant Vision Transformers for Neural PDE Solvers tum-pbs.github.io
Articles & links
Their network
In thuereygroup.bsky.social's orbit
Center = thuereygroup.bsky.social. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.