Related papers: StructBiHOI: Structured Articulation Modeling for …

We investigate a skill-based framework for humanoid box rearrangement that enables long-horizon execution by sequencing reusable skills at the task level. In our architecture, all skills execute through a shared, task-agnostic whole-body…

We address the problem of generating long-horizon videos for robotic manipulation tasks. Text-to-video diffusion models have made significant progress in photorealism, language understanding, and motion generation but struggle with…

In hand object reorientation provides capability for dexterous manipulation, requiring robust control policies to manage diverse object geometries, maintain stable grasps, and execute precise complex orientation trajectories. However, prior…

Bimanual manipulation is a fundamental robotic skill that requires continuous and precise coordination between two arms. While imitation learning (IL) is the dominant paradigm for acquiring this capability, existing approaches, whether…

Despite advances in hand-object interaction modeling, generating realistic dexterous manipulation data for robotic hands remains a challenge. Retargeting methods often suffer from low accuracy and fail to account for hand-object…

Human-Object Interaction (HOI) detection, inferring the relationships between human and objects from images/videos, is a fundamental task for high-level scene understanding. However, HOI detection usually suffers from the open long-tailed…

In this work, we introduce Segmentation to Human-Object Interaction (\textit{\textbf{Seg2HOI}}) approach, a novel framework that integrates segmentation-based vision foundation models with the human-object interaction task, distinguished…

We study the problem of functional retargeting: learning dexterous manipulation policies to track object states from human hand-object demonstrations. We focus on long-horizon, bimanual tasks with articulated objects, which is challenging…

Detecting human-object interaction (HOI) has long been limited by the amount of supervised data available. Recent approaches address this issue by pre-training according to pseudo-labels, which align object regions with HOI triplets parsed…

We address the challenge of creating 3D assets for household articulated objects from a single image. Prior work on articulated object creation either requires multi-view multi-state input, or only allows coarse control over the generation…

Understanding hand-object interaction (HOI) is fundamental to computer vision, robotics, and AR/VR. However, conventional hand videos often lack essential physical information such as contact forces and motion signals, and are prone to…

Recent vision-language-action (VLA) systems have demonstrated strong capabilities in embodied manipulation. However, most existing VLA policies rely on limited observation windows and end-to-end action prediction, which makes them brittle…

Dynamic and dexterous manipulation of objects presents a complex challenge, requiring the synchronization of hand motions with the trajectories of objects to achieve seamless and physically plausible interactions. In this work, we introduce…

Text-guided dynamic 3D character generation has advanced rapidly, yet producing high-quality motion that faithfully reflects rich textual descriptions remains challenging. Existing methods tend to generate limited sub-actions or incoherent…

Imitation learning enables intelligent systems to acquire complex behaviors with minimal supervision. However, existing methods often focus on short-horizon skills, require large datasets, and struggle to solve long-horizon tasks or…

3D hand-object pose estimation is the key to the success of many computer vision applications. The main focus of this task is to effectively model the interaction between the hand and an object. To this end, existing works either rely on…

Enabling robots to flexibly schedule and compose learned skills for novel long-horizon manipulation under diverse perturbations remains a core challenge. Early explorations with end-to-end VLA models show limited success, as these models…

Humans frequently grasp, manipulate, and move objects. Interactive systems assist humans in these tasks, enabling applications in Embodied AI, human-robot interaction, and virtual reality. However, current methods in hand-object synthesis…

Bimanual manipulation is crucial in robotics, enabling complex tasks in industrial automation and household services. However, it poses significant challenges due to the high-dimensional action space and intricate coordination requirements.…

General-purpose robots must master long-horizon manipulation, defined as tasks involving multiple kinematic structure changes (e.g., attaching or detaching objects) in unstructured environments. While Vision-Language-Action (VLA) models…