Contrastive learning has emerged as a promising paradigm for 3D open-world
understanding, jointly with text, image, and point cloud. In this paper, we introduce …

In this supplementary material, we provide detailed dense captioning results on the
ScanRefer dataset in Sec. 1. To showcase the effectiveness of the proposed pre-training …

Environment perception using camera, radar, and/or lidar sensors has significantly improved
in the last few years because of deep learning-based methods. However, a large group of …

Recent work on dense captioning and visual grounding in 3D have achieved impressive
results. Despite developments in both areas, the limited amount of available 3D vision …

A new trend in the computer vision community is to capture objects of interest following
flexible human command represented by a natural language prompt. However, the progress …

We introduce Ferret, a new Multimodal Large Language Model (MLLM) capable of
understanding spatial referring of any shape or granularity within an image and accurately …

Recent works on open-vocabulary 3D instance segmentation show strong promise, but at
the cost of slow inference speed and high computation requirements. This high computation …

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 …

Over the past decades, the addition of hundreds of sensors to modern vehicles has led to an
exponential increase in their capabilities. This allows for novel approaches to interaction …

Humans have a natural ability to effortlessly comprehend linguistic commands such as “park
next to the yellow sedan” and instinctively know which region of the road the vehicle should …