Related papers: GeneralVLA: Generalizable Vision-Language-Action M…
Recent advances in robot manipulation have leveraged pre-trained vision-language models (VLMs) and explored integrating 3D spatial signals into these models for effective action prediction, giving rise to the promising…
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…
The vision-language-action (VLA) paradigm has enabled powerful robotic control by leveraging vision-language models, but its reliance on large-scale, high-quality robot data limits its generalization. Generative world models offer a…
Recent high-capacity vision-language-action (VLA) models have demonstrated impressive performance on a range of robotic manipulation tasks by imitating human demonstrations. However, exploiting offline data with limited visited states will…
The emerging field of Vision-Language-Action (VLA) for humanoid robots faces several fundamental challenges, including the high cost of data acquisition, the lack of a standardized benchmark, and the significant gap between simulation and…
In dynamic environments such as warehouses, hospitals, and homes, robots must seamlessly transition between gross motion and precise manipulations to complete complex tasks. However, current Vision-Language-Action (VLA) frameworks, largely…
Vision-Language-Action (VLA) models are emerging as a promising paradigm for end-to-end autonomous driving, valued for their potential to leverage world knowledge and reason about complex driving scenes. However, existing methods suffer…
The important manifestation of robot intelligence is the ability to naturally interact and autonomously make decisions. Traditional approaches to robot control often compartmentalize perception, planning, and decision-making, simplifying…
Recent advances in Vision-Language-Action (VLA) models have opened new avenues for robot manipulation, yet existing methods exhibit limited efficiency and a lack of high-level knowledge and spatial awareness. To address these challenges, we…
Recent advances in Vision-Language-Action (VLA) models have enabled robotic agents to integrate multimodal understanding with action execution. However, our empirical analysis reveals that current VLAs struggle to allocate visual attention…
This paper proposes to solve the problem of Vision-and-Language Navigation with legged robots, which not only provides a flexible way for humans to command but also allows the robot to navigate through more challenging and cluttered scenes.…
Urban micromobility applications, such as delivery robots, demand reliable navigation across large-scale urban environments while following long-horizon route instructions. This task is particularly challenging due to the dynamic and…
Vision-Language-Action (VLA) models enable robots to interpret natural-language instructions and perform diverse tasks, yet their integration of perception, language, and control introduces new safety vulnerabilities. Despite growing…
Vision-Language-Action (VLA) models have recently achieved remarkable progress in robotic perception and control, yet most existing approaches primarily rely on VLM trained using 2D images, which limits their spatial understanding and…
Vision-Language-Action (VLA) models are driving rapid progress in robotics by enabling agents to interpret multimodal inputs and execute complex, long-horizon tasks. However, their safety and robustness against adversarial attacks remain…
We pursue the goal of developing robots that can interact zero-shot with generic unseen objects via a diverse repertoire of manipulation skills and show how passive human videos can serve as a rich source of data for learning such…
Robotic grasping is a fundamental capability for enabling autonomous manipulation, with usually infinite solutions. State-of-the-art approaches for grasping rely on learning from large-scale datasets comprising expert annotations of…
Recent work on robot manipulation has advanced policy generalization to novel scenarios. However, it is often difficult to characterize how different evaluation settings actually represent generalization from the training distribution of a…
Existing robot policies predominantly adopt the task-centric approach, requiring end-to-end task data collection. This results in limited generalization to new tasks and difficulties in pinpointing errors within long-horizon, multi-stage…
We report our recent progress towards building generalist robot policies, the development of GR-3. GR-3 is a large-scale vision-language-action (VLA) model. It showcases exceptional capabilities in generalizing to novel objects,…