Model Releases

Robbyant releases LingBot-VLA 2.0: an open-source 6B cross-embodiment robot vision-language-action model

Original title:Robbyant Releases LingBot-VLA 2.0: An Open-Source 6B Vision-Language-Action (VLA) Model for Cross-Embodiment Robot Manipulation

AI summary

Robbyant released LingBot-VLA 2.0, a 6B-parameter open-source vision-language-action (VLA) foundation model. It uses Qwen3-VL-4B-Instruct as its backbone and a MoE action expert architecture, representing different robots' states and actions through a unified 55-dimensional canonical vector. Training data covers about 60,000 hours of high-quality data (50,000 hours of robot trajectories plus 10,000 hours of first-person human video), covering 20 robot configurations. On the GM-100 dual-arm benchmark, the model surpasses π0.5 and previous versions across multiple platforms. Model weights, code, and technical report have been open-sourced under the Apache-2.0 license.

Key Takeaways

  • Robbyant released LingBot-VLA 2.
  • 0,a 6B-parameter open-source vision-language-action (VLA) foundation model.
  • It uses Qwen3-VL-4B-Instruct as its backbone and a MoE action expert architecture,representing…
  • Training data covers about 60,000 hours of high-quality data (50,000 hours of robot trajectories…
  • On the GM-100 dual-arm benchmark,the model surpasses π0.

Quick Facts

Published
Updated
Source
MarkTechPost(RSS)
Category
Model Releases
AI score
70
Read the original Read the full article at the original source
Why it matters

蚂蚁Robbyant放出的开源VLA 2.0把通用机器人策略往前推了一步,60,000小时跨具身数据、统一动作空间和MoE设计对做机器人的团队是实打实的参考,不是又一个lab-only的demo。

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Robbyant releases LingBot-VLA 2.0: an open-source 6B cross-embodiment robot vision-language-action model. July 9, 2026. https://new.nat6.net/en/news/cmrcsrok60407ihx5jvrp15a1/

View all →