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

Although generative facial prior and geometric prior have recently demonstrated high-quality
results for blind face restoration, producing fine-grained facial details faithful to inputs …

This work examines the challenges of training neural networks using vector quantization
using straight-through estimation. We find that the main cause of training instability is the …

Abstract Unsupervised image Anomaly Detection (UAD) aims to learn robust and
discriminative representations of normal samples. While separate solutions per class endow …

Monoclonal antibodies have emerged as key therapeutics. In particular, nanobodies, small,
single-domain antibodies that are naturally expressed in camelids, are rapidly gaining …

The success of deep learning comes from its ability to capture the hierarchical structure of
data by learning high-level representations defined in terms of low-level ones. In this paper …

The ability to plan actions on multiple levels of abstraction enables intelligent agents to solve
complex tasks effectively. However, learning the models for both low and high-level …

Vector quantization, renowned for its unparalleled feature compression capabilities, has
been a prominent topic in signal processing and machine learning research for several …

Abstract Vector-Quantized (VQ-based) generative models usually consist of two basic
components ie VQ tokenizers and generative transformers. Prior research focuses on …

Availability of large-scale datasets plays a significant role in segmentation and classification
tasks using deep learning. However, domains such as healthcare inherently suffer from …