The Latent Color Subspace: Emergent Order in High-Dimensional Chaos

MCML Authors

Mateusz Pach

→ Group Zeynep Akata
 Interpretable and Reliable Machine Learning

Jessica Bader

→ Group Zeynep Akata
 Interpretable and Reliable Machine Learning

Quentin Bouniot

Dr.

* Former Member

→ Group Zeynep Akata
 Interpretable and Reliable Machine Learning

Zeynep Akata

Prof. Dr.

Core PI

Interpretable and Reliable Machine Learning

Abstract

Text-to-image generation models have advanced rapidly, yet achieving fine-grained control over generated images remains difficult, largely due to limited understanding of how semantic information is encoded. We develop an interpretation of the color representation in the Variational Autoencoder latent space of FLUX.1 [Dev], revealing a structure reflecting Hue, Saturation, and Lightness. We verify our Latent Color Subspace (LCS) interpretation by demonstrating that it can both predict and explicitly control color, introducing a fully training-free method in FLUX based solely on closed-form latent-space manipulation.

inproceedings PBB+26a

---

ICML 2026

43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available.

---

Authors

M. Pach • J. Bader • Q. Bouniot • S. Belongie • Z. Akata

---

Links

URL GitHub

---

Research Area

 B1 | Computer Vision