MidSteer: Optimal Affine Framework for Steering Generative Models 事件

MidSteer: Optimal Affine Framework for Steering Generative Models arXiv:2605.05220v2 Announce Type: replace-cross Abstract: Steering intermediate representations has emerged as a powerful strategy for controlling generative models, particularly in post-deployment alignment and safety settings. However, despite its empirical success, it currently lacks a comprehensive theoretical framework. In this paper, we bridge this gap by formalizing the theory of concept steering. First, we establish a lin