The Latent Color Subspace: Emergent Order in High-Dimensional Chaos
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. Code is available at https://github.com/ExplainableML/LCS.
Code (0)
등록된 구현이 없습니다.
Tasks
Text-to-Image GenerationSimilar Papers 제목 키워드 기반
Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models
Decades of cognitive science establish that humans navigate environments by forming cognitive maps, defined as allocentric and topology-preserving representations of 3D space. While modern Vision-Language Models (VLMs) d…
Spatial ReasoningWhich Style Makes Me Attractive? Interpretable Control Discovery and Counterfactual Explanation on StyleGAN
The semantically disentangled latent subspace in GAN provides rich interpretable controls in image generation. This paper includes two contributions on semantic latent subspace analysis in the scenario of face generation…
counterfactualCounterfactual ExplanationDisentanglementFace Generation+2Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models
Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning. While recent work has identified structured conceptual representations within these models, it remains unclear whether they func…
Dual-Channel Grounded World Modeling (DCGWM): Structural Prevention of Objective Interference Collapse via Heterogeneous External Grounding with Inward-Only Gradient Flow
Joint Embedding Predictive Architectures (JEPAs) are a leading approach to world model representation learning. We identify a failure mode in JEPA-based world models grounded against two qualitatively distinct external s…
Representation LearningMechanistic Evidence for Spectral Structures in Prior-Data Fitted Networks
Prior-Data Fitted Networks (PFNs) enable amortized Bayesian inference in a single forward pass, yet their internal representations remain opaque. It is unknown whether PFNs encode identifiable Bayesian structure or merel…
Bayesian Inference