LingBot-VA
- AI model
- Humanoids and robot learning
LingBot-VA is an autoregressive video-action world model for robot control that predicts visual dynamics and actions in one interleaved sequence.
Made by Robbyant.
Source on GitHub: github.com/Robbyant/lingbot-va (opens in a new tab). Facts read at commit 7c6ffa9 (opens in a new tab).
Licenses
- Code
- Apache-2.0 (opens in a new tab)
Read by Robotheca from LICENSE.txt (opens in a new tab) (Apache-2.0) at commit 7c6ffa9 (opens in a new tab), on 16 Oct 2026.
- Weights
- Apache-2.0 (opens in a new tab)
Read on huggingface.co/robbyant/lingbot-va-base (opens in a new tab).
- Commercial use
- Yes
What it does
- Unifies visual dynamics prediction and action inference in a single interleaved autoregressive sequence.
- Uses a dual-stream mixture-of-transformers architecture with asynchronous execution and KV cache for efficiency.
- Provides inference and evaluation on RoboTwin-2.0 and LIBERO through a server-client setup.
- Supports image-to-video-action generation from a single input image.
- Offers post-training code for fine-tuning on custom manipulation datasets in LeRobot format.
- Reports results on RoboTwin 2.0, LIBERO, and six real-world manipulation tasks.
Written by Robotheca from the project's README (opens in a new tab) at commit 7c6ffa9.
Getting started
- Difficulty
- Advanced
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Maintained: a commit in the last 12 months
- Newest commit
- 9 Jul 2026 on main
- Latest release
- None published on GitHub
Checked on GitHub on 16 Oct 2026.
Links
Robots on Robotheca that use it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists AI models as a reference: nothing is hosted or run here, and every fact links to where it was read.