4 papers
FullFlow: Upgrading Text-to-Image Flow Matching Models for Bidirectional Vision--Language Generation
Eric Tillmann Bill, Enis Simsar, Alessio Tonioni +1
Modern text-to-image diffusion models encode rich visual priors, but expose them only through one-way text-conditioned generation. Existing unified vision--language models derived…
FOCUS: Optimal Control for Multi-Entity World Modeling in Text-to-Image Generation
Eric Tillmann Bill, Enis Simsar, Thomas Hofmann
Text-to-image (T2I) models excel on single-entity prompts but struggle with multi-entity scenes, often exhibiting attribute leakage, identity entanglement, and subject omissions. W…
Exploring Magnitude Preservation and Rotation Modulation in Diffusion Transformers
Eric Tillman Bill, Cristian Perez Jensen, Sotiris Anagnostidis +1
Denoising diffusion models exhibit remarkable generative capabilities, but remain challenging to train due to their inherent stochasticity, where high-variance gradient estimates l…
JEDI: The Force of Jensen-Shannon Divergence in Disentangling Diffusion Models
Eric Tillmann Bill, Enis Simsar, Thomas Hofmann
We introduce JEDI, a test-time adaptation method that enhances subject separation and compositional alignment in diffusion models without requiring retraining or external supervisi…