A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
The paper shows that vision foundation models can serve as effective tokenizers for latent diffusion models, but distillation-based tokenizer training weakens performance.
Siting Li, Zhengyang Wang, Simon Shaolei Du, et al.
A controlled autoregressive testbed shows image tokenizers act as visual languages, with task-specific losses revealing distinct scaling and downstream links.
Andrey Shutkin, Denis Parkhomenko, Ivan Kirillov, et al.
KVAE introduces a family of tokenizers for audio, image, and video that match or surpass frontier open-source tokenizers in reconstruction and generation quality.