Related papers: Scalable Video-to-Dataset Generation for Cross-Pla…
Learning multimodal video understanding typically relies on datasets comprising video clips paired with manually annotated captions. However, this becomes even more challenging when dealing with long-form videos, lasting from minutes to…
Visual navigation tasks are critical for household service robots. As these tasks become increasingly complex, effective communication and collaboration among multiple robots become imperative to ensure successful completion. In recent…
Large language models (LLMs) have demonstrated remarkable capabilities across a range of text-generation tasks. However, LLMs still struggle with problems requiring multi-step decision-making and environmental feedback, such as online…
Digital agents require diverse, large-scale UI trajectories to generalize across real-world tasks, yet collecting such data is prohibitively expensive in both human annotation, infra and engineering perspectives. To this end, we introduce…
Many recent advancements in Computer Vision are attributed to large datasets. Open-source software packages for Machine Learning and inexpensive commodity hardware have reduced the barrier of entry for exploring novel approaches at scale.…
We propose a novel approach for captioning and object grounding in video, where the objects in the caption are grounded in the video via temporally dense bounding boxes. We introduce the following contributions. First, we present a…
The task of long-term action anticipation demands solutions that can effectively model temporal dynamics over extended periods while deeply understanding the inherent semantics of actions. Traditional approaches, which primarily rely on…
World models - generative models that simulate environment dynamics conditioned on past observations and actions - are gaining prominence in planning, simulation, and embodied AI. However, evaluating their rollouts remains a fundamental…
Early screening via colonoscopy is critical for colon cancer prevention, yet developing robust AI systems for this domain is hindered by the lack of densely annotated, long-sequence video datasets. Existing datasets predominantly focus on…
Understanding and modeling human mobility patterns is crucial for effective transportation planning and urban development. Despite significant advances in mobility research, there remains a critical gap in simulation platforms that allow…
In recent years, large-scale models have achieved significant advancements, accompanied by the emergence of numerous high-quality benchmarks for evaluating various aspects of their comprehension abilities. However, most existing benchmarks…
The rapid progress of navigation, manipulation, and vision models has made mobile manipulators capable in many specialized tasks. However, the open-world mobile manipulation (OWMM) task remains a challenge due to the need for generalization…
Instructional videos are a common source for learning text-video or even multimodal representations by leveraging subtitles extracted with automatic speech recognition systems (ASR) from the audio signal in the videos. However, in contrast…
Video-based large language models (Video-LLMs) have been recently introduced, targeting both fundamental improvements in perception and comprehension, and a diverse range of user inquiries. In pursuit of the ultimate goal of achieving…
We present TextMonkey, a large multimodal model (LMM) tailored for text-centric tasks. Our approach introduces enhancement across several dimensions: By adopting Shifted Window Attention with zero-initialization, we achieve cross-window…
Mobile device agent based on Multimodal Large Language Models (MLLM) is becoming a popular application. In this paper, we introduce Mobile-Agent, an autonomous multi-modal mobile device agent. Mobile-Agent first leverages visual perception…
Common knowledge indicates that the process of constructing image datasets usually depends on the time-intensive and inefficient method of manual collection and annotation. Large models offer a solution via data generation. Nonetheless,…
Large language models (LLMs) have demonstrated strong performance in sentence-level machine translation, but scaling to document-level translation remains challenging, particularly in modeling long-range dependencies and discourse phenomena…
Understanding animals' behaviors is significant for a wide range of applications. However, existing animal behavior datasets have limitations in multiple aspects, including limited numbers of animal classes, data samples and provided tasks,…
In this paper, we tackle the problem of how to build and benchmark a large motion model (LMM). The ultimate goal of LMM is to serve as a foundation model for versatile motion-related tasks, e.g., human motion generation, with…