LingBot-VA2.0 Focuses on Embodied Native Pretraining
机器之心 · wechat · 2026-07-10
The article introduces Ant Group's LingBot-VA2.0, claiming it as the industry's first "embodied native" pretrained model. Designed from the ground up—across data, training objectives, and architecture—for robots to accomplish tasks in the real physical world. It employs an autoregressive video generation approach for pretraining, allowing the model to predict the next state of the world while generating actions.
Related event: LingBot-VA/VLA 2.0 Released: Native Embodied Foundation Model(24 posts)→
More from Embodied
- Nothing phone mockup turns a film joke into a modular design meme — ZeYanjie · 2026-07-22
- Lightwheel AI Launches SimReadyGen: Text-to-Physics-Accurate Robot Sim Assets — ZeYanjie · 2026-07-22
- Humanoid robot sorting packages in a warehouse sparks debate over job loss — MonaJalal_ · 2026-07-22
- NVIDIA pushes OpenUSD as the common layer for simulation and physical AI — MonaJalal_ · 2026-07-22
- A quadruped robot gets a custom glow-up with a new shell and screen — DynamicWebPaige · 2026-07-22
- A VR teleop demo for an SO-101 arm gets absurdly low latency by using one Python script — MoonL88537 · 2026-07-22