Related papers: IntentVLA: Short-Horizon Intent Modeling for Alias…

General-purpose robots must master long-horizon manipulation, defined as tasks involving multiple kinematic structure changes (e.g., attaching or detaching objects) in unstructured environments. While Vision-Language-Action (VLA) models…

Vision-Language-Action (VLA) models trained via imitation learning suffer from significant performance degradation in data-scarce scenarios due to their reliance on large-scale demonstration datasets. Although reinforcement learning…

Prevalent Vision-Language-Action (VLA) models are typically built upon Multimodal Large Language Models (MLLMs) and demonstrate exceptional proficiency in semantic understanding, but they inherently lack the capability to deduce physical…

Vision-Language-Action (VLA) models have gained much attention from the research community thanks to their strength in translating multimodal observations with linguistic instructions into desired robotic actions. Despite their…

Vision-based robotic policies often struggle with even minor viewpoint changes, underscoring the need for view-invariant visual representations. This challenge becomes more pronounced in real-world settings, where viewpoint variability is…

Most existing vision-language-action (VLA) models for robotic manipulation lack progress awareness, typically relying on hand-crafted heuristics for task termination. This limitation is particularly severe in long-horizon tasks involving…

Vision-language-action (VLA) models are effective robot action executors, but they remain limited on long-horizon tasks due to the dual burden of extended closed-loop planning and diverse physical operations. We therefore propose…

Although large vision-language-action (VLA) models pretrained on extensive robot datasets offer promising generalist policies for robotic learning, they still struggle with spatial-temporal dynamics in interactive robotics, making them less…

Despite advances in Vision-Language-Action (VLA) models, robotic manipulation struggles with fine-grained tasks because current models lack mechanisms for active visual attention allocation. Human gaze naturally encodes intent, planning,…

The performance of robotic imitation learning is fundamentally limited by data quality and training strategies. Prevalent sampling strategies on RLBench suffer from severe keyframe redundancy and imbalanced temporal distribution, leading to…

Bridging high-level semantic understanding with low-level physical control remains a persistent challenge in embodied intelligence, stemming from the fundamental spatiotemporal scale mismatch between cognition and action. Existing…

Equipping embodied agents with the ability to reason about tasks, foresee physical outcomes, and generate precise actions is essential for general-purpose manipulation. While recent Vision-Language-Action (VLA) models have leveraged…

Deploying autonomous robots that can learn new skills from demonstrations is an important challenge of modern robotics. Existing solutions often apply end-to-end imitation learning with Vision-Language Action (VLA) models or symbolic…

Vision-Language-Action (VLA) models, as large foundation models for embodied control, have shown strong performance in manipulation tasks. However, their performance comes at high inference cost. To improve efficiency, recent methods adopt…

Vision language action (VLA) models enable generalist robotic agents but often exhibit language ignorance, relying on visual shortcuts and remaining insensitive to instruction changes. We present Prospective Grounding and Alignment VLA…

Vision-language-action models (VLAs) have shown potential in leveraging pretrained vision-language models and diverse robot demonstrations for learning generalizable sensorimotor control. While this paradigm effectively utilizes large-scale…

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…

Real-world embodied agents face long-horizon tasks, characterized by high-level goals demanding multi-step solutions beyond single actions. Successfully navigating these requires both high-level task planning (i.e., decomposing goals into…

Vision-Language-Action (VLA) models commonly adapt pretrained Vision-Language Models (VLMs) to robot control by mapping visual observations and language instructions to continuous actions. Existing approaches typically take an…

Despite significant progress in Visual-Language-Action (VLA), in highly complex and dynamic environments that involve real-time unpredictable interactions (such as 3D open worlds and large-scale PvP games), existing approaches remain…