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 …

With the rise of big data, the quality of datasets has become a crucial factor affecting the
performance of machine learning models. High-quality datasets are essential for the …

Abstract We introduce the Segment Anything (SA) project: a new task, model, and dataset for
image segmentation. Using our efficient model in a data collection loop, we built the largest …

Abstract This work presents Depth Anything a highly practical solution for robust monocular
depth estimation. Without pursuing novel technical modules we aim to build a simple yet …

Large vision-language models (VLMs) have recently achieved remarkable progress,
exhibiting impressive multimodal perception and reasoning abilities. However, effectively …

The scaling of Transformers has driven breakthrough capabilities for language models. At
present, the largest large language models (LLMs) contain upwards of 100B parameters …

Diffusion model (DM) has achieved SOTA performance by modeling the image synthesis
process into a sequential application of a denoising network. However, different from image …

We present Unified-IO 2 a multimodal and multi-skill unified model capable of following
novel instructions. Unified-IO 2 can use text images audio and/or videos as input and can …

Recent accelerations in multi-modal applications have been made possible with the
plethora of image and text data available online. However, the scarcity of analogous data in …

Abstract Out-of-distribution (OOD) detection is a critical task for deploying machine learning
models in the open world. Distance-based methods have demonstrated promise, where …