We present the training recipe and results of scaling up PaLI-X, a multilingual vision and
language model, both in terms of size of the components and the breadth of its training task …

We explore the boundaries of scaling up a multilingual vision and language model both in
terms of size of the components and the breadth of its training task mixture. Our model …

Effective scaling and a flexible task interface enable large language models to excel at many
tasks. We present PaLI (Pathways Language and Image model), a model that extends this …

In this work, we introduce the Qwen-VL series, a set of large-scale vision-language models
(LVLMs) designed to perceive and understand both texts and images. Starting from the …

Much of vision-and-language research focuses on a small but diverse set of independent
tasks and supporting datasets often studied in isolation; however, the visually-grounded …

In this work, we introduce the Qwen-VL series, a set of large-scale vision-language models
(LVLMs) designed to perceive and understand both texts and images. Starting from 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 …

A big convergence of language, multimodal perception, action, and world modeling is a key
step toward artificial general intelligence. In this work, we introduce KOSMOS-1, a …

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 state …

We introduce LAVIS, an open-source deep learning library for LAnguage-VISion research
and applications. LAVIS aims to serve as a one-stop comprehensive library that brings …