As information exists in various modalities in real world, effective interaction and fusion
among multimodal information plays a key role for the creation and perception of multimodal …

Large pre-trained models, also known as foundation models (FMs), are trained in a task-
agnostic manner on large-scale data and can be adapted to a wide range of downstream …

Text-to-image synthesis has recently seen significant progress thanks to large pretrained
language models, large-scale training data, and the introduction of scalable model families …

Recent advances in personalized image generation have enabled pre-trained text-to-image
models to learn new concepts from specific image sets. However these methods often …

Large-scale text-to-image diffusion models can generate high-fidelity images with powerful
compositional ability. However, these models are typically trained on an enormous amount …

Neural compression is the application of neural networks and other machine learning
methods to data compression. Recent advances in statistical machine learning have opened …

We investigate the potential of learning visual representations using synthetic images
generated by text-to-image models. This is a natural question in the light of the excellent …

The stunning qualitative improvement of text-to-image models has led to their widespread
attention and adoption. However, we lack a comprehensive quantitative understanding of …

We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that
efficiently samples large-scale foundational image diffusion models in just 1-4 steps while …

The most advanced text-to-image (T2I) models require significant training costs (eg, millions
of GPU hours), seriously hindering the fundamental innovation for the AIGC community …