Deep generative models are a class of techniques that train deep neural networks to model
the distribution of training samples. Research has fragmented into various interconnected …

By decomposing the image formation process into a sequential application of denoising
autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image …

Score-based generative models (SGMs) have recently demonstrated impressive results in
terms of both sample quality and distribution coverage. However, they are usually applied …

Diffusion models learn to restore noisy data, which is corrupted with different levels of noise,
by optimizing the weighted sum of the corresponding loss terms, ie, denoising score …

Pretraining language models with next-token prediction on massive text corpora has
delivered phenomenal zero-shot, few-shot, transfer learning and multi-tasking capabilities …

Score-based generative models (SGMs) have demonstrated remarkable synthesis quality.
SGMs rely on a diffusion process that gradually perturbs the data towards a tractable …

Diffusion models are rising as a powerful solution for high-fidelity image generation, which
exceeds GANs in quality in many circumstances. However, their slow training and inference …

Although neural text-to-speech (TTS) models have attracted a lot of attention and succeeded
in generating human-like speech, there is still room for improvements to its naturalness and …

Attention-based models, exemplified by the Transformer, can effectively model long range
dependency, but suffer from the quadratic complexity of self-attention operation, making …

Controllable generation is one of the key requirements for successful adoption of deep
generative models in real-world applications, but it still remains as a great challenge. In …