Visual prompt engineering is a fundamental methodology in the field of visual and image
artificial general intelligence. As the development of large vision models progresses, the …

This monograph surveys vision-language pre-training (VLP) methods for multimodal
intelligence that have been developed in the last few years. We group these approaches …

Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks
(DNNs) training, and they usually train a DNN for each single visual recognition task …

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

In this work, we discuss building performant Multimodal Large Language Models (MLLMs).
In particular, we study the importance of various architecture components and data choices …

In this work, we introduce Semantic-SAM, an augmented image segmentation foundation for
segmenting and recognizing anything at desired granularities. Compared to the …

Traditional 3D scene understanding approaches rely on labeled 3D datasets to train a
model for a single task with supervision. We propose OpenScene, an alternative approach …

Pre-trained vision-language (VL) models such as CLIP have shown excellent generalization
ability to downstream tasks. However, they are sensitive to the choice of input text prompts …

Prompt learning has emerged as an efficient alternative for fine-tuning foundational models,
such as CLIP, for various downstream tasks. Conventionally trained using the task-specific …

Prompt tuning is an effective way to adapt the pretrained visual-language model (VLM) to
the downstream task using task-related textual tokens. Representative CoOp-based works …