13 papers
Realtime-VLA V2: Learning to Run VLAs Fast, Smooth, and Accurate
Chen Yang, Yucheng Hu, Yunchao Ma +3
In deployment of the VLA models to real-world robotic tasks, execution speed matters. In previous work arXiv:2510.26742 we analyze how to make neural computation of VLAs on GPU fas…
Robotic Scene Cloning:Advancing Zero-Shot Robotic Scene Adaptation in Manipulation via Visual Prompt Editing
Binyuan Huang, Yuqing Wen, Yucheng Zhao +5
Modern robots can perform a wide range of simple tasks and adapt to diverse scenarios in the well-trained environment. However, deploying pre-trained robot models in real-world use…
DM0: An Embodied-Native Vision-Language-Action Model towards Physical AI
En Yu, Haoran Lv, Jianjian Sun +46
Moving beyond the traditional paradigm of adapting internet-pretrained models to physical tasks, we present DM0, an Embodied-Native Vision-Language-Action (VLA) framework designed…
MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
Hao Shi, Bin Xie, Yingfei Liu +7
Temporal context is essential for robotic manipulation because such tasks are inherently non-Markovian, yet mainstream VLA models typically overlook it and struggle with long-horiz…
SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation
Hao Shi, Bin Xie, Yingfei Liu +5
Robotic manipulation requires precise spatial understanding to interact with objects in the real world. Point-based methods suffer from sparse sampling, leading to the loss of fine…
Running VLAs at Real-time Speed
Yunchao Ma, Yizhuang Zhou, Yunhuan Yang +2
In this paper, we show how to run pi0-level multi-view VLA at 30Hz frame rate and at most 480Hz trajectory frequency using a single consumer GPU. This enables dynamic and real-time…