Related papers: Humanoid-VLA: Towards Universal Humanoid Control w…
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…
Vision-language-action (VLA) models have demonstrated strong semantic understanding and zero-shot generalization, yet most existing systems assume an accurate low-level controller with hand-crafted action "vocabulary" such as end-effector…
Vision-language-action models have emerged as a crucial paradigm in robotic manipulation. However, existing VLA models exhibit notable limitations in handling ambiguous language instructions and unknown environmental states. Furthermore,…
General-purpose humanoid robots are expected to interact intuitively with humans, enabling seamless integration into daily life. Natural language provides the most accessible medium for this purpose. However, translating language into…
Robotic generalization relies on physical intelligence: the ability to reason about state changes, contact-rich interactions, and long-horizon planning under egocentric perception and action. Vision Language Models (VLMs) are essential to…
Prevailing Vision-Language-Action Models (VLAs) for robotic manipulation are built upon vision-language backbones pretrained on large-scale, but disconnected static web data. As a result, despite improved semantic generalization, the policy…
We introduce Green-VLA, a staged Vision-Language-Action (VLA) framework for real-world deployment on the Green humanoid robot while maintaining generalization across diverse embodiments. Green-VLA follows a five stage curriculum: (L0)…
Vision-language-action (VLA) models show potential for general robotic tasks, but remain challenging in spatiotemporally coherent manipulation, which requires fine-grained representations. Typically, existing methods embed 3D positions into…
Recent advances in vision-language-action (VLA) models have shown promise in integrating image generation with action prediction to improve generalization and reasoning in robot manipulation. However, existing methods are limited to…
We aim to build complex humanoid agents that integrate perception, motor control, and memory. In this work, we partly factor this problem into low-level motor control from proprioception and high-level coordination of the low-level skills…
Exploring open-world situations in an end-to-end manner is a promising yet challenging task due to the need for strong generalization capabilities. In particular, end-to-end autonomous driving in unstructured outdoor environments often…
Humanoid robots hold great potential to perform various human-level skills, involving unified locomotion and manipulation in real-world settings. Driven by advances in machine learning and the strength of existing model-based approaches,…
While leveraging abundant human videos and simulated robot data poses a scalable solution to the scarcity of real-world robot data, the generalization capability of existing vision-language-action models (VLAs) remains limited by mismatches…
Vision-language-action models (VLAs) have garnered significant attention for their potential in advancing robotic manipulation. However, previous approaches predominantly rely on the general comprehension capabilities of vision-language…
In this paper, we introduce a novel kinematics-rich vision-language-action (VLA) task, in which language commands densely encode diverse kinematic attributes (such as direction, trajectory, orientation, and relative displacement) from…
The rapid progress of auto-regressive vision-language models (VLMs) has inspired growing interest in vision-language-action models (VLA) for robotic manipulation. Recently, masked diffusion models, a paradigm distinct from autoregressive…
Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from perception to action,…
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…
Humanoid robots that can autonomously operate in diverse environments have the potential to help address labour shortages in factories, assist elderly at homes, and colonize new planets. While classical controllers for humanoid robots have…
Vision-Language-Action models (VLAs) are emerging as powerful tools for learning generalizable visuomotor control policies. However, current VLAs are mostly trained on large-scale image-text-action data and remain limited in two key ways:…