Related papers: HieroAction: Hierarchically Guided VLM for Fine-Gr…
AI agents powered by Large Language Models (LLMs) have made significant advances, enabling them to assist humans in diverse complex tasks and leading to a revolution in human-AI coordination. LLM-powered agents typically require invoking…
Reinforcement learning has been successful in many tasks ranging from robotic control, games, energy management etc. In complex real world environments with sparse rewards and long task horizons, sample efficiency is still a major…
Visual-Language-Action models (VLAs) have advanced generalist robot control by mapping multimodal observations and language instructions directly to actions, but sparse action supervision often encourages shortcut mappings rather than…
The robust recognition and assessment of human actions are crucial in human-robot interaction (HRI) domains. While state-of-the-art models of action perception show remarkable results in large-scale action datasets, they mostly lack the…
We present a vision-action policy that won 1st place in the 2025 BEHAVIOR Challenge - a large-scale benchmark featuring 50 diverse long-horizon household tasks in photo-realistic simulation, requiring bimanual manipulation, navigation, and…
Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language models (LVLMs) typically adopt a single-pass reasoning paradigm…
Bridging the gap between natural language commands and autonomous execution in unstructured environments remains an open challenge for robotics. This requires robots to perceive and reason over the current task scene through multiple…
Fine-tuning vision-language models (VLMs) on robot teleoperation data to create vision-language-action (VLA) models is a promising paradigm for training generalist policies, but it suffers from a fundamental tradeoff: learning to produce…
Recent advances in vision-language models (VLMs) have achieved impressive results on standard image-text tasks, yet their potential for visual procedure question answering (VP-QA) remains largely unexplored. VP-QA presents unique challenges…
Current vision-language models (VLMs) are well-adapted for general visual understanding tasks. However, they perform inadequately when handling complex visual tasks related to human poses and actions due to the lack of specialized…
We present Vision in Action (ViA), an active perception system for bimanual robot manipulation. ViA learns task-relevant active perceptual strategies (e.g., searching, tracking, and focusing) directly from human demonstrations. On the…
Human-Robot Collaboration (HRC) plays an important role in assembly tasks by enabling robots to plan and adjust their motions based on interactive, real-time human instructions. However, such instructions are often linguistically ambiguous…
Action recognition has become a rapidly developing research field within the last decade. But with the increasing demand for large scale data, the need of hand annotated data for the training becomes more and more impractical. One way to…
Goal-oriented planning, or anticipating a series of actions that transition an agent from its current state to a predefined objective, is crucial for developing intelligent assistants aiding users in daily procedural tasks. The problem…
Sequence models in reinforcement learning require task knowledge to estimate the task policy. This paper presents a hierarchical algorithm for learning a sequence model from demonstrations. The high-level mechanism guides the low-level…
Recent multimodal large language models (MLLMs) have advanced video understanding, yet most still "think about videos" ie once a video is encoded, reasoning unfolds entirely in text, treating visual input as a static context. This passive…
Solving long-horizon tasks requires robots to integrate high-level semantic reasoning with low-level physical interaction. While vision-language models (VLMs) and video generation models can decompose tasks and imagine outcomes, they often…
We present HaoMo Vision-Language Model (HMVLM), an end-to-end driving framework that implements the slow branch of a cognitively inspired fast-slow architecture. A fast controller outputs low-level steering, throttle, and brake commands,…
Existing action quality assessment (AQA) methods mainly learn deep representations at the video level for scoring diverse actions. Due to the lack of a fine-grained understanding of actions in videos, they harshly suffer from low…
Text-to-motion generation, which synthesizes 3D human motions from text inputs, holds immense potential for applications in gaming, film, and robotics. Recently, diffusion-based methods have been shown to generate more diversity and…