Dyna-2
Dyna Robotics
Dyna-2 is Dyna Robotics' world-action model, pre-trained on more than one million hours of egocentric human video and evaluated on held-out human and robot data.
- Code
- Unverified
- Weights
- Unverified
- Checkpoint
- Unverified
- License
- Unverified
Decision summary
World-action modeling from large-scale human video
Workflows that require publicly downloadable weights or code
Verify repository and artifact licenses.
Release history
Source-backed release timing for this canonical model record.
- Company release date evidence
Model release
Release timing is recorded from official model metadata.
Evidence profile
A visual read of adoption evidence. Scores describe catalog evidence readiness, not task performance.
Published evaluation
1/6
dimensions scored
Unknown evidence remains visible and is never treated as a zero.
Why these scores
The strongest decision reasons behind the evidence profile.
Artifact availability
UnknownCode and weights are not verified.
Training and loading reproducibility
UnknownNo verified loading configuration is available.
Evaluation evidence
UnknownNo structured evaluation evidence has been verified.
Data requirements
Declared loop-data needs, missing evidence, and the next checks that matter.
Observation / ego video
Video observations
Action / robot state
Robot action trajectories · Proprioception
Sim-real / embodiment metadata
Robot action trajectories
Critical gaps
Core categories are represented. Interface alignment and data quality still require verification.
Linked datasets
Signal-level links only. Verify runtime interfaces before use.
No related catalog datasets are linked to this model yet.
More evidenceShowHide
Additional decision dimensions
License or access terms are not verified.
— · c20Required signal categories are structured; exact tensor and action interfaces still need verification.
76 · c70Hardware, latency, dependencies, and checkpoint loading are not pipeline-tested.
— · c10Artifact facts
- catalog.curation
- openbot_inference
- tier: editorial_focus · collection: OpenBot important model releases · policy: human_curated_priority
- OpenBot editorial release selection
- model.type
- official_claim
- World-action model (WAM)
- Official release title and introduction
- model.reported_scale
- official_claim
- pretraining video hours: 1,000,000+ · source: human egocentric video
- Official release abstract and Figure 1
- model.required_signals
- openbot_inference
- Video observations · Robot action trajectories · Proprioception
- OpenBot signal mapping from the official architecture description
- release_timing
- metadata_verified
- 2026-08-10T00:00:00.000Z
- Existing published Catalog release-date evidence
Additional references
OpenBot notes
- Published performance and scaling results are source-reported claims, not OpenBot pipeline tests.
- The official release does not list a public code, weight, checkpoint, or license artifact.
