Related papers: SeqVLA: Sequential Task Execution for Long-Horizon…

Vision-Language-Action (VLA) models trained on large robot datasets promise general-purpose, robust control across diverse domains and embodiments. However, existing approaches often fail out-of-the-box when deployed in novel environments,…

To build a generalizable Vision-Language-Action (VLA) model with strong reasoning ability, a common strategy is to first train a specialist VLA on robot demonstrations to acquire reliable manipulation skills, and then incorporate mixed…

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…

Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robotic manipulation, leveraging large-scale pre-training to achieve strong performance. The field has rapidly evolved with additional spatial…

Learning universal policies from cross-embodied data remains a fundamental challenge in robotics. Although Vision-Language-Action (VLA) models are pre-trained on large and diverse datasets, they typically rely on embodiment-specific…

Vision-Language-Action (VLA) models map visual observations and language instructions directly to robotic actions. While effective for simple tasks, standard VLA models often struggle with complex, multi-step tasks requiring logical…

Vision-language-action (VLA) models have significantly advanced robotic manipulation by enabling robots to interpret language instructions for task execution. However, training these models often relies on large-scale user-specific data,…

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,…

Developing robust and general-purpose manipulation policies represents a fundamental objective in robotics research. While Vision-Language-Action (VLA) models have demonstrated promising capabilities for end-to-end robot control, existing…

Manipulating dynamic objects remains an open challenge for Vision-Language-Action (VLA) models, which, despite strong generalization in static manipulation, struggle in dynamic scenarios requiring rapid perception, temporal anticipation,…

Despite their strong performance in embodied tasks, recent Vision-Language-Action (VLA) models remain highly fragile under multimodal perturbations, where visual corruption and linguistic noise jointly induce distribution shifts that…

Vision-Language-Action (VLA) models fail systematically on long-horizon manipulation tasks despite strong short-horizon performance. We show that this failure is not resolved by extending context length alone in the current reactive…

This research introduces the Bi-VLA (Vision-Language-Action) model, a novel system designed for bimanual robotic dexterous manipulation that seamlessly integrates vision for scene understanding, language comprehension for translating human…

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…

Vision-language-action (VLA) models for closed-loop robot control are typically cast under the Markov assumption, making them prone to errors on tasks requiring historical context. To incorporate memory, existing VLAs either retrieve from a…

Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The performance of VLA models can be improved by integrating with action chunking, a critical technique for effective control.…

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…

Robot imitation data are often multimodal: similar visual-language observations may be followed by different action chunks because human demonstrators act with different short-horizon intents, task phases, or recent context. Existing…

Existing Vision-Language-Action (VLA) models often struggle to generalize to long-horizon tasks due to their heavy reliance on immediate observations. While recent studies incorporate retrieval mechanisms or extend context windows to handle…

Robotic foundation models achieve strong generalization by leveraging internet-scale vision-language representations, but their massive computational cost creates a fundamental bottleneck: high inference latency. In dynamic environments,…