AIBullisharXiv – CS AI · 10h ago7/10
🧠
EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers
EquiformerV3, an advanced SE(3)-equivariant graph neural network, achieves significant improvements in efficiency, expressivity, and generality for 3D atomistic modeling. The new version delivers 1.75x speedup, introduces architectural innovations like SwiGLU-S² activations and smooth-cutoff attention, and achieves state-of-the-art results on major molecular modeling benchmarks including OC20 and OMat24.
$SE