Robot AI model
LingBot-VLA
LingBot-VLA is a manipulation foundation model pretrained on real-world dual-arm robot trajectories. Robbyant publishes depth-free and depth-distilled checkpoints, post-training code and evaluations on AgiBot G1 and Galaxea R1 Pro.
Records last verified Oct 13, 2026 · Send a correction
Also known as LingBot-VLA-4B
- Organization
- Robbyant
- Type
- VLA
- Released / introduced
- Jan 27, 2026
- Public weights
- Public weights
- Licence / scope
- Apache-2.0
- Parameters
- 4B
- Base model
- Qwen2.5-VL-3B-Instruct
- Humanoid association
- Humanoid demonstrated
- Inputs
- vision, language
- 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.
- AgiBot G1 →
Real-robot evaluation table in the official repository.
- Galaxea R1 Pro →
R1 Pro evaluation; the catalog groups the R1 variants.
Disclosed training data
- Robbyant multi-configuration dual-arm robot trajectories
More robot AI models
Evidence
Sources
- [s1] LingBot-VLA official README: release, backbone and real-robot evaluations ↗
Robbyant · official · accessed Oct 13, 2026
- [s2] LingBot-VLA-4B official model card ↗
Robbyant · official · accessed Oct 13, 2026
- [s3] A Pragmatic VLA Foundation Model ↗
Robbyant · paper · published Jan 26, 2026 · accessed Oct 13, 2026