Related papers: ABot-PhysWorld: Interactive World Foundation Model…
Generative world models are increasingly used for video generation, where learned simulators are expected to capture the physical rules that govern real-world dynamics. However, evaluating whether generated videos actually follow these…
Video diffusion models provide powerful real-world simulators for embodied AI but remain limited in controllability for robotic manipulation. Recent works on trajectory-conditioned video generation address this gap but often rely on 2D…
In the rapidly advancing field of robotics, dual-arm coordination and complex object manipulation are essential capabilities for developing advanced autonomous systems. However, the scarcity of diverse, high-quality demonstration data and…
Text-to-video generative models have made significant strides in recent years, producing high-quality videos that excel in both aesthetic appeal and accurate instruction following, and have become central to digital art creation and user…
The generalization of vision-language-action (VLA) models heavily relies on diverse training data. However, acquiring large-scale data for robot manipulation across varied object appearances is costly and labor-intensive. To address this…
Being able to simulate the outcomes of actions in varied environments will revolutionize the development of generalist agents at scale. However, modeling these world dynamics, especially for dexterous robotics tasks, poses significant…
The human-like form of humanoid robots positions them uniquely to achieve the agility and versatility in motor skills that humans possess. Learning from human demonstrations offers a scalable approach to acquiring these capabilities.…
The embodied intelligence bridges the physical world and information space. As its typical physical embodiment, humanoid robots have shown great promise through robot learning algorithms in recent years. In this study, a hardware platform,…
Robots are traditionally bounded by a fixed embodiment during their operational lifetime, which limits their ability to adapt to their surroundings. Co-optimizing control and morphology of a robot, however, is often inefficient due to the…
In this work, we rethink the approach to video super-resolution by introducing a method based on the Diffusion Posterior Sampling framework, combined with an unconditional video diffusion transformer operating in latent space. The video…
We present PhysGen, a novel image-to-video generation method that converts a single image and an input condition (e.g., force and torque applied to an object in the image) to produce a realistic, physically plausible, and temporally…
Recent robot foundation models largely rely on large-scale behavior cloning, which imitates expert actions but discards transferable dynamics knowledge embedded in heterogeneous embodied data. While the Unified World Model (UWM) formulation…
Validating Augmented Reality (AR) tracking and interaction models requires precise, repeatable ground-truth motion. However, human users cannot reliably perform consistent motion due to biomechanical variability. Robotic manipulators are…
Joint audio-video generation models are rapidly approaching professional production quality, raising a central question: do they understand audio-visual physics, or merely generate plausible sounds and frames that violate real-world…
World models have emerged as promising neural simulators for autonomous driving, with the potential to supplement scarce real-world data and enable closed-loop evaluations. However, current research primarily evaluates these models based on…
In the rapidly advancing field of robotics, dual-arm coordination and complex object manipulation are essential capabilities for developing advanced autonomous systems. However, the scarcity of diverse, high-quality demonstration data and…
Robot manipulation in the real world is fundamentally constrained by the visual sim2real gap, where depth observations collected in simulation fail to reflect the complex noise patterns inherent to real sensors. In this work, inspired by…
Enabling robots to execute novel manipulation tasks zero-shot is a central goal in robotics. Most existing methods assume in-distribution tasks or rely on fine-tuning with embodiment-matched data, limiting transfer across platforms. We…
Building general-purpose embodied agents across diverse hardware remains a central challenge in robotics, often framed as the ''one-brain, many-forms'' paradigm. Progress is hindered by fragmented data, inconsistent representations, and…
Diffusion models have significantly improved the performance of image editing. Existing methods realize various approaches to achieve high-quality image editing, including but not limited to text control, dragging operation, and…