3 papers
Purrception: Variational Flow Matching for Vector-Quantized Image Generation
RÄzvan-Andrei MatiÅan, Vincent Tao Hu, Grigory Bartosh +6
We introduce Purrception, a variational flow matching approach for vector-quantized image generation that provides explicit categorical supervision while maintaining continuous tra…
NARAIM: Native Aspect Ratio Autoregressive Image Models
Daniel Gallo Fernández, Robert van der Klis, RÄzvan-Andrei MatiÅan +4
While vision transformers are able to solve a wide variety of computer vision tasks, no pre-training method has yet demonstrated the same scaling laws as observed in language model…
DuoDiff: Accelerating Diffusion Models with a Dual-Backbone Approach
Daniel Gallo Fernández, RÄzvan-Andrei MatiÅan, Alejandro Monroy Muñoz +4
Diffusion models have achieved unprecedented performance in image generation, yet they suffer from slow inference due to their iterative sampling process. To address this, early-ex…