Robot AI model
LingBot-VLA 2.0
LingBot-VLA 2.0 expands the training mixture, action representation and predictive-dynamics objectives of LingBot-VLA. Its native-depth checkpoint uses Qwen3-VL, and the repository reports real manipulation results on Galaxea R1 Pro.
Records last verified Oct 13, 2026 · Send a correction
Also known as LingBot-VLA-V2, LingBot-VLA-v2-6B
- Organization
- Robbyant
- Type
- VLA
- Released / introduced
- Jul 8, 2026
- Public weights
- Public weights
- Licence / scope
- Apache-2.0
- Parameters
- 6B
- Base model
- Qwen3-VL-4B-Instruct
- Humanoid association
- Humanoid demonstrated
- Inputs
- vision, language, depth
- Outputs
- robot actions
Release dates can mark an announcement or paper introduction. Public checkpoints, code licences and weight terms are distinct; follow the publisher’s links for the stated scope.
Documented embodiments
Source-associated hardware; this list does not establish plug-and-play compatibility or commercial robot capability.
- Galaxea R1 Pro →
Real-robot evaluation table in the official repository; the catalog groups the R1 variants.
Disclosed training data
- Robbyant robot-trajectory and egocentric human-video mixture
More robot AI models
Evidence
Sources
- [s1] LingBot-VLA 2.0 official README: release, training and real-robot evaluations ↗
Robbyant · official · accessed Oct 13, 2026
- [s2] LingBot-VLA 2.0 6B official model card ↗
Robbyant · official · accessed Oct 13, 2026
- [s3] From Foundation to Application: Improving VLA Models in Practice ↗
Robbyant · paper · published Jul 7, 2026 · accessed Oct 13, 2026