Newest papers

FocusVLA: Future-Intent Guided Dynamic View Routing for Vision-Language-Action Models

Huixin Xu, Ziya Yu, Peng Li · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31423 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

Os modelos Focus-language-action (VLA) da visão-foco se tornaram um paradigma importante para a manipulação robótica, unificando a percepção visual, a compreensão da linguagem e a geração de ação. Uma vez que a manipulação confiável requer observação suficiente de objetos, efeitos finais e suas relações espaciais, as entradas multi-view são amplamente usadas para fornecer informações espaciais complementares. No entanto, nossos experimentos mostram que os modelos VLA existentes não exploram plenamente essa complementaridade multi-view. A política tende a depender persistentemente da visão do pulso, sem a capacidade de ajustar dinamicamente a dependência de visão global-local em todas as fases de manipulação, o que limita a adaptabilidade e robustez do estágio. Para resolver este problema,

Machine translation (Meta M2M100); the English original follows.

Abstract

Vision-language-action (VLA) models have become an important paradigm for robotic manipulation by unifying visual perception, language understanding, and action generation. Since reliable manipulation requires sufficient observation of objects, end-effectors, and their spatial relationships, multi-view inputs are widely used to provide complementary spatial information. However, our experiments show that existing VLA models do not fully exploit such multi-view complementarity. The policy tends to persistently rely on the wrist view, lacking the ability to dynamically adjust global-local view dependency across manipulation stages, which limits stage adaptability and robustness. To address this issue, we propose FocusVLA, a stage-aware multi-view routing framework. FocusVLA predicts future interaction intent from historical actions and uses it to guide dynamic view routing during action generation. By adaptively coordinating global and local observations across different task stages, FocusVLA improves multi-view utilization. On RoboTwin 2.0, FocusVLA improves the average success rate over the strongest baseline $π_{0.5}$ by 10.10 pp. In real-world evaluation, FocusVLA improves the success rate from 71.7\% to 85.0\%, achieving a 13.3\% gain over $π_{0.5}$. Moreover, the intent prediction and dynamic routing modules of FocusVLA can be integrated into existing VLA frameworks without modifying their core architectures.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Exploit, Adaptability, Task (project management), Routing (electronic design automation), Dependency (UML)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange