4 papers
NABLA: Neighborhood Adaptive Block-Level Attention
Dmitrii Mikhailov, Aleksey Letunovskiy, Maria Kovaleva +6
Recent progress in transformer-based architectures has demonstrated remarkable success in video generation tasks. However, the quadratic complexity of full attention mechanisms rem…
Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation
Vladimir Arkhipkin, Vladimir Korviakov, Nikolai Gerasimenko +22
This report introduces Kandinsky 5.0, a family of state-of-the-art foundation models for high-resolution image and 10-second video synthesis. The framework comprises three core lin…
Time-Correlated Video Bridge Matching
Viacheslav Vasilev, Arseny Ivanov, Nikita Gushchin +2
Diffusion models excel in noise-to-data generation tasks, providing a mapping from a Gaussian distribution to a more complex data distribution. However, they struggle to model tran…
VIVAT: Virtuous Improving VAE Training through Artifact Mitigation
Lev Novitskiy, Viacheslav Vasilev, Maria Kovaleva +2
Variational Autoencoders (VAEs) remain a cornerstone of generative computer vision, yet their training is often plagued by artifacts that degrade reconstruction and generation qual…