Despite its success in image synthesis, we observe that diffusion probabilistic models
(DPMs) often lack contextual reasoning ability to learn the relations among object parts in an …

The great success of Large Language Models (LLMs) has expanded the potential of
multimodality, contributing to the gradual evolution of General Artificial Intelligence (AGI). A …

Vector Quantisation (VQ) is experiencing a comeback in machine learning, where it is
increasingly used in representation learning. However, optimizing the codevectors in …

We present a unified transformer, ie, Show-o, that unifies multimodal understanding and
generation. Unlike fully autoregressive models, Show-o unifies autoregressive and …

Recent advances in generative compression methods have demonstrated remarkable
progress in enhancing the perceptual quality of compressed data, especially in scenarios …

Amortized Bayesian inference trains neural networks to solve stochastic inference problems
using model simulations, thereby making it possible to rapidly perform Bayesian inference …

Vector quantization (VQ) is a key technique in high-resolution and high-fidelity image
synthesis, which aims to learn a codebook to encode an image with a sequence of discrete …

Despite its success in image synthesis, we observe that diffusion probabilistic models
(DPMs) often lack contextual reasoning ability to learn the relations among object parts in an …