Abstract Pretrained Foundation Models (PFMs) are regarded as the foundation for various
downstream tasks across different data modalities. A PFM (eg, BERT, ChatGPT, GPT-4) is …

Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

The recent breakthroughs in natural language processing for model pretraining on large
quantities of data have opened the way for similar foundation models in computer vision …

We present ImageBind, an approach to learn a joint embedding across six different
modalities-images, text, audio, depth, thermal, and IMU data. We show that all combinations …

A big convergence of language, vision, and multimodal pretraining is emerging. In this work,
we introduce a general-purpose multimodal foundation model BEiT-3, which achieves …

Scale is the primary factor for building a powerful foundation model that could well
generalize to a variety of downstream tasks. However, it is still challenging to train video …

Finding correspondences between images is a fundamental problem in computer vision. In
this paper, we show that correspondence emerges in image diffusion models without any …

This paper demonstrates an approach for learning highly semantic image representations
without relying on hand-crafted data-augmentations. We introduce the Image-based Joint …

We survey applications of pretrained foundation models in robotics. Traditional deep
learning models in robotics are trained on small datasets tailored for specific tasks, which …

Abstract We propose Cut-and-LEaRn (CutLER), a simple approach for training
unsupervised object detection and segmentation models. We leverage the property of self …