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
- ECCV26 Oral: Flow Matching Enables Single-Stage Multi-View Point Cloud Registration — ducha_aiki · 2026-09-11
- Polish developers build iPhone app that detects nearby Meta smart glasses — Low-Honeydew6483 · 2026-09-11
- Ant's Afu health AI hits 150M users, unveils AI+hardware health alliance at Bund Summit — APPSO · 2026-09-11
- Johns Hopkins Launches Full-Stack Hands-on Robot Learning Class with SO-101 Arm Kits — _krishna_murthy · 2026-09-11
- SyncWorld: In-Context Robot World Model Simulates Unseen Views and Embodiments Zero-Shot — ChongZzZhang · 2026-09-11
- A 3D Pose Dataset for Dogs Released — ducha_aiki · 2026-09-11