Part of Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Main Conference Track
Zihao Wang, Lin Gui, Jeffrey Negrea, Victor Veitch
This paper concerns the structure of learned representations in text-guided generative models, focusing on score-based models. A key property of such models is that they can compose disparate concepts in a 'disentangled' manner.This suggests these models have internal representations that encode concepts in a 'disentangled' manner. Here, we focus on the idea that concepts are encoded as subspaces of some representation space. We formalize what this means, show there's a natural choice for the representation, and develop a simple method for identifying the part of the representation corresponding to a given concept. In particular, this allows us to manipulate the concepts expressed by the model through algebraic manipulation of the representation. We demonstrate the idea with examples using Stable Diffusion.