Related papers: SOP: A Scalable Online Post-Training System for Vi…

Integrating visual-language instructions into visuomotor policies is gaining momentum in robot learning for enhancing open-world generalization. Despite promising advances, existing approaches face two challenges: limited language…

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…

Generalization in robot manipulation is essential for deploying robots in open-world environments and advancing toward artificial general intelligence. While recent Vision-Language-Action (VLA) models leverage large pre-trained…

Foundation models applied in robotics, particularly \textbf{Vision--Language--Action (VLA)} models, hold great promise for achieving general-purpose manipulation. Yet, systematic real-world evaluations and cross-model comparisons remain…

Current Vision-Language-Action (VLA) models predominantly rely on end-to-end fine-tuning. While effective, this paradigm compromises the inherent generalization capabilities of Vision-Language Models (VLMs) and incurs catastrophic…

Robotic manipulation is a fundamental component of automation. However, traditional perception-planning pipelines often fall short in open-ended tasks due to limited flexibility, while the architecture of a single end-to-end…

Vision-Language-Action (VLA) models, trained via flow-matching or diffusion objectives, excel at learning complex behaviors from large-scale, multi-modal datasets (e.g., human teleoperation, scripted policies). However, since VLAs…

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…

Fine-tuning vision-language models (VLMs) on robot teleoperation data to create vision-language-action (VLA) models is a promising paradigm for training generalist policies, but it suffers from a fundamental tradeoff: learning to produce…

Recent vision-language-action models (VLAs) build upon pretrained vision-language models and leverage diverse robot datasets to demonstrate strong task execution, language following ability, and semantic generalization. Despite these…

Vision-Language-Action (VLA) models show promise in embodied reasoning, yet remain far from true generalists-they often require task-specific fine-tuning, incur high compute costs, and generalize poorly to unseen tasks. We propose MetaVLA,…

Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robotic control, with test-time scaling (TTS) gaining attention to enhance robustness beyond training. However, existing TTS methods for VLAs…

Building generalist embodied agents requires integrating perception, language understanding, and action, which are core capabilities addressed by Vision-Language-Action (VLA) approaches based on multimodal foundation models, including…

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…

Recent Vision-Language-Action (VLA) models built on pre-trained Vision-Language Models (VLMs) require extensive post-training, resulting in high computational overhead that limits scalability and deployment.We propose CogVLA, a…

Built upon language and vision foundation models with strong generalization ability and trained on large-scale robotic data, Vision-Language-Action (VLA) models have recently emerged as a promising approach to learning generalist robotic…

Training end-to-end policies from image data to directly predict navigation actions for robotic systems has proven inherently difficult. Existing approaches often suffer from either the sim-to-real gap during policy transfer or a limited…

The emergence of vision-language-action (VLA) models has given rise to foundation models for robot manipulation. Although these models have achieved significant improvements, their generalization in multi-task manipulation remains limited.…

We introduce VIOLA, an object-centric imitation learning approach to learning closed-loop visuomotor policies for robot manipulation. Our approach constructs object-centric representations based on general object proposals from a…

Recent progress in Reinforcement Learning (RL) provides a principled approach to optimizing Vision-Language-Action (VLA) models, facilitating a shift from trajectory imitation to active learning in the task environment. Despite improvements…