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 …

Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …

We present LLaMA-Adapter, a lightweight adaption method to efficiently fine-tune LLaMA
into an instruction-following model. Using 52K self-instruct demonstrations, LLaMA-Adapter …

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 …

Abstract Universal Image Segmentation is not a new concept. Past attempts to unify image
segmentation include scene parsing, panoptic segmentation, and, more recently, new …

Pre-trained vision-language models (eg, CLIP) have shown promising zero-shot
generalization in many downstream tasks with properly designed text prompts. Instead of …

Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of machine
learning systems. For instance, in autonomous driving, we would like the driving system to …

Large-scale pre-trained models have shown promising open-world performance for both
vision and language tasks. However, their transferred capacity on 3D point clouds is still …

Large pre-trained vision-language models like CLIP have shown great potential in learning
representations that are transferable across a wide range of downstream tasks. Different …

Recently, zero-shot and few-shot learning via Contrastive Vision-Language Pre-training
(CLIP) have shown inspirational performance on 2D visual recognition, which learns to …