Related papers: GeoPredict: Leveraging Predictive Kinematics and 3…

Vision-Language-Action (VLA) models often fail to generalize to unseen camera viewpoints, a limitation stemming from their difficulty in inferring robust 3D geometry from 2D images. We introduce GeoAware-VLA, a simple yet effective approach…

Vision-Language-Action (VLA) models have emerged as a promising approach for enabling robots to follow language instructions and predict corresponding actions. However, current VLA models mainly rely on 2D visual inputs, neglecting the rich…

Vision-language-action (VLA) policies have advanced language-conditioned robotic manipulation by transferring semantic priors from pretrained vision-language models to action generation. However, standard action-imitation learning often…

At its core, robotic manipulation is a problem of vision-to-geometry mapping ($f(v) \rightarrow G$). Physical actions are fundamentally defined by geometric properties like 3D positions and spatial relationships. Consequently, we argue that…

Spatial perception and reasoning are crucial for Vision-Language-Action (VLA) models to accomplish fine-grained manipulation tasks. However, existing approaches often lack the ability to understand and reason over the essential 3D…

Bimanual manipulation requires policies that can reason about 3D geometry, anticipate how it evolves under action, and generate smooth, coordinated motions. However, existing methods typically rely on 2D features with limited spatial…

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…

3D-aware visual pretraining has proven effective in improving the performance of downstream robotic manipulation tasks. However, existing methods are constrained to Euclidean embedding spaces, whose flat geometry limits their ability to…

Vision-Language-Action (VLA) models provide a promising paradigm for robot learning by integrating visual perception with language-guided policy learning. However, most existing approaches rely on 2D visual inputs to perform actions in 3D…

In this paper, we claim that spatial understanding is the keypoint in robot manipulation, and propose SpatialVLA to explore effective spatial representations for the robot foundation model. Specifically, we introduce Ego3D Position Encoding…

Most existing Vision-Language-Action (VLA) models rely primarily on RGB information, while ignoring geometric cues crucial for spatial reasoning and manipulation. In this work, we introduce GLaD, a geometry-aware VLA framework that…

Predictive foresight is important to intelligent embodied agents. Since the motor execution of a robot is intrinsically constrained by its visual perception of environmental geometry, effectively anticipating the future requires capturing…

Mobile manipulation is the fundamental challenge for robotics to assist humans with diverse tasks and environments in everyday life. However, conventional mobile manipulation approaches often struggle to generalize across different tasks…

Robotic manipulation in 3D requires effective computation of N degree-of-freedom joint-space trajectories that enable precise and robust control. To achieve this, robots must integrate semantic understanding with visual perception to…

Vision-language-action (VLA) models perform well on training-seen robotic tasks but struggle to generalize to unseen scenes and objects. A key limitation lies in their implicit visual representations, which entangle object appearance,…

Vision-language-action models (VLAs) have shown generalization capabilities in robotic manipulation tasks by inheriting from vision-language models (VLMs) and learning action generation. Most VLA models focus on interpreting vision and…

Vision-language-action (VLA) models integrate visual observations and language instructions to predict robot actions, demonstrating promising generalization in manipulation tasks. However, most existing approaches primarily rely on direct…

Large foundation models have shown strong open-world generalization to complex problems in vision and language, but similar levels of generalization have yet to be achieved in robotics. One fundamental challenge is that the models exhibit…

Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-specific action supervision. Since these models typically rely…

Vision-Language-Action (VLA) models show promise for robotic control, yet performance in complex household environments remains sub-optimal. Mobile manipulation requires reasoning about global scene layout, fine-grained geometry, and…