lie-groups

SE(3)-MeanFlow introduces a few-step generative framework for protein backbone generation on Lie groups, extending MeanFlow to SE(3) with closed-form average-velocity training targets and a rectification-based post-training that matches or exceeds flow-matching baselines at reduced sampling steps.

Proposes LieBN, a framework for batch normalization over Lie groups, applicable to SPD, rotation, and correlation manifolds, with theoretical guarantees and extensive experiments.

This paper proposes Lie group embedded dynamical neural networks (LieEDNN) with learning algorithms based on gradient descent and metric projection on smooth manifolds, enabling stable dynamics on Lie groups like SO(3) and SE(3) for robotics and control applications.