Related papers: World-Ego Modeling for Long-Horizon Evolution in H…
Training robot policies within a learned world model is trending due to the inefficiency of real-world interactions. The established image-based world models and policies have shown prior success, but lack robust geometric information that…
Standard Chain-of-Thought (CoT) prompting empowers Large Language Models (LLMs) with reasoning capabilities, yet its reliance on linear natural language is inherently insufficient for effective world modeling in embodied tasks. While text…
World models have emerged as a critical frontier in AI research, aiming to enhance large models by infusing them with physical dynamics and world knowledge. The core objective is to enable agents to understand, predict, and interact with…
Language model (LM)-based embodied agents are increasingly deployed in real-world settings. Yet, their adaptability remains limited in dynamic environments, where constructing accurate and flexible world models is crucial for effective…
World models aim to learn action-controlled future prediction and have proven essential for the development of intelligent agents. However, most existing world models rely heavily on substantial action-labeled data and costly training,…
In egocentric scenarios, anticipating both the next action and its visual outcome is essential for understanding human-object interactions and for enabling robotic planning. However, existing paradigms fall short of jointly modeling these…
Agent self-improvement, where the backbone Large Language Model (LLM) of the agent are trained on trajectories sampled autonomously based on their own policies, has emerged as a promising approach for enhancing performance. Recent…
World models (WMs) demonstrate strong capabilities in prediction, generation, and planning tasks. Existing WMs primarily focus on unstructured data and cannot leverage the ubiquitous structured data, often represented as graphs, in the…
The rapid evolution of egocentric video analysis brings new insights into understanding human activities and intentions from a first-person perspective. Despite this progress, the fragmentation in tasks like action recognition, procedure…
Learning natural, stable, and compositionally generalizable whole-body control policies for humanoid robots performing simultaneous locomotion and manipulation (loco-manipulation) remains a fundamental challenge in robotics. Existing…
Legged locomotion over various terrains is challenging and requires precise perception of the robot and its surroundings from both proprioception and vision. However, learning directly from high-dimensional visual input is often…
Human egocentric video captures rich manipulation demonstrations without any robot hardware, yet transferring these skills to robots remains challenging due to the embodiment gap between human and robot in both visual appearance and…
Humans are known to have an internal "world model" that enables us to carry out action planning based on world states. AI agents need to have such a world model for action planning as well. It is not clear how current AI models, especially…
Long-horizon tasks in robotic manipulation present significant challenges in reinforcement learning (RL) due to the difficulty of designing dense reward functions and effectively exploring the expansive state-action space. However, despite…
Understanding human behavior from complementary egocentric (ego) and exocentric (exo) points of view enables the development of systems that can support workers in industrial environments and enhance their safety. However, progress in this…
We propose Infinite-World, a robust interactive world model capable of maintaining coherent visual memory over 1000+ frames in complex real-world environments. While existing world models can be efficiently optimized on synthetic data with…
Estimating 3D human motion from an egocentric video sequence plays a critical role in human behavior understanding and has various applications in VR/AR. However, naively learning a mapping between egocentric videos and human motions is…
We introduce LHM-Humanoid, a benchmark and learning framework for long-horizon whole-body humanoid loco-manipulation in diverse, cluttered scenes. In our setting, multiple objects are displaced from their intended locations and may obstruct…
Action-conditioned video prediction models (often referred to as world models) have shown strong potential for robotics applications, but existing approaches are often slow and struggle to capture physically consistent interactions over…
Embodied agents in household environments must plan under partial observation: they need to remember objects, track state changes, and recover when actions fail. Existing benchmarks only partially test this ability. Egocentric video…