Preprint
Aug 2026
KVAE: Family of Tokenizers for Multimodal Generative Models
It is demonstrated that reconstruction and generation results on objective and subjective metrics matches or surpasses frontier opensource tokenizers, such as VAEs from Wan-2.2, HunyuanVideo-1.5, FLUX.2, MovieGen, StableAudio and MMAudio.
Andrey Shutkin, Denis Parkhomenko, Ivan Kirillov et al.
· 0 citations