arXiv:2603.12261v1 Announce Type: cross
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. Code is available at https://github.com/ExplainableML/LCS.
Trust and anxiety as primary drivers of digital health acceptance in multiple sclerosis: toward an extended disease-specific technology acceptance model
BackgroundDigital health applications and AI-supported wearables may benefit people with Multiple Sclerosis (MS), yet fluctuating cognitive and physical symptoms could shape adoption in ways not