The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …

Image restoration (IR) has been an indispensable and challenging task in the low-level
vision field, which strives to improve the subjective quality of images distorted by various …

Large-scale multimodal generative modeling has created milestones in text-to-image and
text-to-video generation. Its application to audio still lags behind for two main reasons: the …

Large-scale generative models such as GPT and DALL-E have revolutionized the research
community. These models not only generate high fidelity outputs, but are also generalists …

Large language models (LLMs) have exhibited remarkable capabilities across a variety of
domains and tasks, challenging our understanding of learning and cognition. Despite the …

Typical diffusion models are trained to accept a particular form of conditioning, most
commonly text, and cannot be conditioned on other modalities without retraining. In this …

The immense scale of the recent large language models (LLM) allows many interesting
properties, such as, instruction-and chain-of-thought-based fine-tuning, that has significantly …

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading
performances in many generative tasks. However, the inherited iterative sampling process …

Diffusion models are state-of-the-art deep learning empowered generative models that are
trained based on the principle of learning forward and reverse diffusion processes via …

Text-to-image diffusion models often make implicit assumptions about the world when
generating images. While some assumptions are useful (eg, the sky is blue), they can also …