LingBot-VLA 2.0: Built for Robot Control
bendee983 · x · 2026-07-11
To address the high latency and lack of action cognition when directly adapting video models for robotics, LingBot-VLA 2.0 is trained from scratch specifically for robot control.
Its core architecture features a visual tokenizer, action prediction, and a full causal Transformer. The model leverages web-scale video (including human demonstrations) for scalable self-supervised learning to capture action-relevant visual dynamics.
Evaluation Performance:
- Rapidly adapts with only 10-15 demonstrations
- Supports transfer across different robot embodiments
- Achieves a 93.6% score on the RoboTwin 2.0 benchmark
Related event: LingBot-VA/VLA 2.0 Released: Native Embodied Foundation Model(24 posts)→
More from Embodied
- The Humanoid AI raises $152M Series A at a $1.35B valuation — RazRazcle · 2026-07-22
- SceniX joins World Labs to close the real-to-sim gap for robot learning — davidyin44 · 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
- NVIDIA says physical AI starts in simulation with OpenUSD and synthetic data — MonaJalal_ · 2026-07-22