Vision systems to see and reason about the compositional nature of visual scenes are
fundamental to understanding our world. The complex relations between objects and their …

As a special type of transformer, vision transformers (ViTs) can be used for various computer
vision (CV) applications. Convolutional neural networks (CNNs) have several potential …

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 …

We introduce Kosmos-2, a Multimodal Large Language Model (MLLM), enabling new
capabilities of perceiving object descriptions (eg, bounding boxes) and grounding text to the …

Large language models have shown their remarkable capabilities as a general interface for
various language-related applications. Motivated by this, we target to build a unified …

We present X-Decoder, a generalized decoding model that can predict pixel-level
segmentation and language tokens seamlessly. X-Decoder takes as input two types of …

In this paper, we present a new sequence-to-sequence learning framework for visual
tracking, dubbed SeqTrack. It casts visual tracking as a sequence generation problem …

We introduce CogVLM, a powerful open-source visual language foundation model. Different
from the popular shallow alignment method which maps image features into the input space …

All instance perception tasks aim at finding certain objects specified by some queries such
as category names, language expressions, and target annotations, but this complete field …

Abstract Referring Expression Segmentation (RES) aims to generate a segmentation mask
for the object described by a given language expression. Existing classic RES datasets and …