OpenBot
Back to models
VLAOpen2026model hub

LingBot-VLA 2.0

Robbyant

A whole-body VLA release focused on broader cross-embodiment transfer, mobile manipulation, and predictive dynamics supervision.

Best for

Whole-body action generation

Primary blocker

Track as a release in the LingBot-VLA series rather than an unrelated model.

Evidence rule

A model hub link is a declaration. Files, loadability, evaluation, and deployment are scored separately.

Family
VLA
Signals
6 tracked
Datasets
3 linked

Model decision scorecard

Use-case scores and evidence confidence are separate; Unknown is not treated as failure.

2 unresolved dimensions

Code, weights, and checkpoints

Useful
65confidence 40

An official model hub is linked; weight files and loadability are not verified.

Loading and training reproducibility

Unknown
confidence 15

No verified loading configuration is available.

Training data requirements

Useful
76confidence 50

Required signal categories are declared; exact tensor and action interfaces still need verification.

Evaluation evidence

Useful
68confidence 40

Evaluation focus is declared, but metrics are not independently verified.

Deployment readiness

Unknown
confidence 10

Hardware, latency, dependencies, and runtime loading are not yet verified.

Artifact facts and provenance

No metadata-verified artifact facts yet. Source links remain declarations only.

Loop signal demand

Signals this model family needs for training, evaluation, or failure mining.

5 required categories

Observation / ego video

observation · Human video paired with robot data

required

Language intent / task phase

language intent · task phase · Long-horizon task phases

required

Action / robot state

actions · robot state · Whole-body action traces · Whole-body action generation

required

Future state / dynamics

future state

required

Feedback / correction / failure

Needs success, failure, correction, or recovery signals to turn evaluation into better data.

useful

Sim-real / embodiment metadata

robot state · Multiple robot configurations · Human video paired with robot data · Out-of-distribution embodiment transfer

required

Evaluation focus

  • Whole-body action generation
  • Long-horizon mobile manipulation
  • Out-of-distribution embodiment transfer

Missing critical loop signals

Core signal demands are represented. Check quality, alignment, and access constraints.

Related catalog datasets

OpenBot notes

  • Track as a release in the LingBot-VLA series rather than an unrelated model.

Related models