Related papers: Objaverse: A Universe of Annotated 3D Objects

Seemingly simple natural language requests to a robot are generally underspecified, for example "Can you bring me the wireless mouse?" Flat images of candidate mice may not provide the discriminative information needed for "wireless." The…

Recently, 3D scenes parsing with deep learning approaches has been a heating topic. However, current methods with fully-supervised models require manually annotated point-wise supervision which is extremely user-unfriendly and…

Selection of occluded objects is a challenging problem in virtual reality, even more so if multiple objects are involved. With the advent of new artificial intelligence technologies, we explore the possibility of leveraging large language…

The field of 4D world modeling - aiming to jointly capture spatial geometry and temporal dynamics - has witnessed remarkable progress in recent years, driven by advances in large-scale generative models and multimodal learning. However, the…

Point tracking aims to follow visual points through complex motion, occlusion, and viewpoint changes, and has advanced rapidly with modern foundation models. Yet progress toward general point tracking remains constrained by limited…

As AI-driven document understanding and processing tools become increasingly prevalent in real-world applications, the need for rigorous evaluation standards has grown increasingly urgent. Existing benchmarks and evaluations often focus on…

It is commonly acknowledged that the availability of the huge amount of (training) data is one of the most important factors for many recent advances in Artificial Intelligence (AI). However, datasets are often designed for specific tasks…

The advancement of Embodied AI heavily relies on large-scale, simulatable 3D scene datasets characterized by scene diversity and realistic layouts. However, existing datasets typically suffer from limitations in data scale or diversity,…

Artificial Intelligence (AI) and its applications have sparked extraordinary interest in recent years. This achievement can be ascribed in part to advances in AI subfields including Machine Learning (ML), Computer Vision (CV), and Natural…

Large-scale datasets play a vital role in computer vision. But current datasets are annotated blindly without differentiation to samples, making the data collection inefficient and unscalable. The open question is how to build a mega-scale…

Document understanding tasks, in particular, Visually-rich Document Entity Retrieval (VDER), have gained significant attention in recent years thanks to their broad applications in enterprise AI. However, publicly available data have been…

General visual representations learned from web-scale datasets for robotics have achieved great success in recent years, enabling data-efficient robot learning on manipulation tasks; yet these pre-trained representations are mostly on 2D…

While Large Vision Language Models (LVLMs) are increasingly deployed in real-world applications, their ability to interpret abstract visual inputs remains limited. Specifically, they struggle to comprehend hand-drawn sketches, a modality…

Recent advances in multimodal large language models (MLLMs) have expanded research in video understanding, primarily focusing on high-level tasks such as video captioning and question-answering. Meanwhile, a smaller body of work addresses…

The use of large pretrained neural networks to create contextualized word embeddings has drastically improved performance on several natural language processing (NLP) tasks. These computationally expensive models have begun to be applied to…

Being data-driven is one of the most iconic properties of deep learning algorithms. The birth of ImageNet drives a remarkable trend of "learning from large-scale data" in computer vision. Pretraining on ImageNet to obtain rich universal…

With the recent rise of large language models, vision-language models, and other general foundation models, there is growing potential for multimodal, multi-task robotics that can operate in diverse environments given natural language…

Large scale image dataset and deep convolutional neural network (DCNN) are two primary driving forces for the rapid progress made in generic object recognition tasks in recent years. While lots of network architectures have been…

In recent years many different deep neural networks were developed, but due to a large number of layers in deep networks, their training requires a long time and a large number of datasets. Today is popular to use trained deep neural…

Object detection is crucial for ensuring safe autonomous driving. However, data-driven approaches face challenges when encountering minority or novel objects in the 3D driving scene. In this paper, we propose VisLED, a language-driven…