Abstract We introduce Generative Infinite-Vocabulary Transformers (GIVT) which generate
vector sequences with real-valued entries, instead of discrete tokens from a finite …

We propose to replace vector quantization (VQ) in the latent representation of VQ-VAEs with
a simple scheme termed finite scalar quantization (FSQ), where we project the VAE …

In recent years, neural network-driven image compression (NIC) has gained significant
attention. Some works adopt deep generative models such as GANs and diffusion models to …

Image compression aims to minimize the amount of data in image representation while
maintaining a certain visual quality for humans, which is an essential technique for storage …

Image compression methods based on machine learning have achieved high rate-distortion
performance. However, the reconstructions they produce suffer from blurring at extremely …

Early detection of cognitive impairment is a pivotal interdisciplinary research area in
contemporary cognitive neuroscience. Researchers employ multimodal data, including brain …

Learning based image compression has achieved impressive rate-distortion performance in
recent years. However, due to the disposable learning strategy and rigid network …

Multiple Description Coding (MDC) is a promising error-resilient source coding method that
is particularly suitable for dynamic networks with multiple (yet noisy and unreliable) paths …

Learned image compression (LIC) is increasingly gaining attention. To improve the
perceptual quality of reconstructions, generative LIC has been studied, using generative …

Lossy image coding is the art of computing that is principally bounded by the image's rate-
distortion function. This bound, though never accurately characterized, has been …