LingBot-VLA 2.0 Leads in Empirical Tests
omarsar0 · x · 2026-07-15
This update shares the empirical results of LingBot-VLA 2.0.
- Under the generalist setting across 9 GM-100 desktop tasks, it overall outperforms π₀.₅ and GR00T N1.7 on two different robot platforms.
- It maintains a lead in long-horizon mobile tasks; for example, in the stove cleaning task, it achieved an out-of-domain success rate of 40%, higher than π₀.₅'s 33.3%.
- This demonstrates that it can not only perform desktop manipulation but also coordinate the head, waist, chassis, robotic arm, and hand to complete cross-room, long-horizon tasks.
Related event: Ant Group unveils LingBot-VLA 2.0 for cross-embodiment robot control(8 posts)→
More from Embodied
- Atoms raises $1.7B as investors bet on AI moving into the physical world — ivory_tang · 2026-07-23
- A Killer App for Humanoid Robots: Teleoperation and Telepresence — adam_dorr · 2026-07-23
- Proprio Robotics pitches robots for autonomous data centers as AI strains the grid — ycombinator · 2026-07-23
- W&B says world action models can show their “dream” before choosing actions — wandb · 2026-07-23
- W&B says NVIDIA’s 14B DreamZero model fails hard tasks despite clean scalar metrics — wandb · 2026-07-23
- Musk says Optimus could become Tesla’s biggest product and rewrites the labor equation — r0ck3t23 · 2026-07-23