Riemannian-Manifold Steering: Geometry-Aware Generative Autoencoders for Label-Free Steering

ArXi:2605.24942v1 Announce Type: cross Steering a language model - intervening on its internal activations to change downstream behaviour - has recently expanded beyond linear interpolation to nonlinear methods such as angular and kernelized steering, which define intervention transformations without learning an explicit geometry over paths in activation space. Freshly