5 papers
HyperbolicDiffusion: Sharp & Scalable Tiled Generation on the Hyperbolic Plane
Hugo Caselles-Dupré
Planar tiled diffusion denoises overlapping windows of one rectangular canvas. The hyperbolic plane has no such canvas, and its area grows exponentially with radius. We introduce H…
FrescoDiffusion: 4K Image-to-Video with Prior-Regularized Tiled Diffusion
Hugo Caselles-Dupré, Mathis Koroglu, Guillaume Jeanneret +2
Diffusion-based image-to-video (I2V) models are increasingly effective, yet they struggle to scale to ultra-high-resolution inputs (e.g., 4K). Generating videos at the model's nati…
Proportion and Perspective Control for Flow-Based Image Generation
Julien Boudier, Hugo Caselles-Dupré
While modern text-to-image diffusion models generate high-fidelity images, they offer limited control over the spatial and geometric structure of the output. To address this, we in…
Weaving the Future: Generative AI and the Reimagining of Fashion Design
Pierre-Marie Chauvin, Angèle Merlin, Xavier Fresquet +3
This paper explores the integration of generative AI into the fashion design process. Drawing on insights from the January 2025 seminar ``Tisser le futur,'' it investigates how AI…
Utility-based Adaptive Teaching Strategies using Bayesian Theory of Mind
Clémence Grislain, Hugo Caselles-Dupré, Olivier Sigaud +1
Good teachers always tailor their explanations to the learners. Cognitive scientists model this process under the rationality principle: teachers try to maximise the learner's util…