LingBot-VA 2.0 Embodied Model Released
JaynitMakwana · x · 2026-07-10
LingBot-VA 2.0 features a joint video-action modeling approach that predicts the next state while simultaneously planning actions, which the authors argue is more natural than traditional reactive robotic models.
Described as the first embodied-native foundation model rather than a fine-tuned video generation model, it reportedly achieves a 93.6% success rate on bimanual tasks, 150Hz inference on a single GPU, and generalization from 20 demos.
Related event: Ant Lingbo Open-Sources LingBot-VLA 2.0 for Multi-Robot Generalization(18 posts)→
More from Embodied
- Bedrock Robotics raises $600M as its fully autonomous excavators do paid work on live job sites — Sethwinterroth · 2026-10-27
- AW-0 hits 80.8% on RoboTwin tasks, beating strongest baseline by 16 points — trevordarrell · 2026-10-27
- AW-0's code stream fixes world model prediction: picks mango where baseline grabs apple — trevordarrell · 2026-10-27
- AW-0 runs at 230ms on a single RTX 5090, 2.4x faster than autoregressive code planning — trevordarrell · 2026-10-27
- AW-0 debuts: one generative world action model plans in code, predicts, and controls robots — trevordarrell · 2026-10-27
- Skyfall AI's SKY-001 world model turns sketches into CAD builds in 3.9s, vs 199s for GPT-6 Astra — rohanpaul_ai · 2026-10-27