2 papers
cs.RO2026
RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?
Zhenxuan Fan, Bo Zhang, Yutong Lin +9
Vision-Language-Action (VLA) models have shown promising progress in language-conditioned robotic manipulation. However, existing datasets and benchmarks mainly evaluate task compl…
cs.CV2026
Iron: Intent-Aligned and Retrospective Dual Learning Framework for Enhancing Generalist Virtual Agents
Jiahe Ying, Wendong Bu, Kaihang Pan +6
Achieving virtual agents capable of automating tasks across diverse digital environments remains a pivotal challenge in Embodied AI. While Multimodal Large Language Models (MLLMs)…