OA-WAM
Research
Object-addressable world-action model that decomposes scenes into robot and object slots while jointly predicting future world state and actions.
Object identity under scene shifts
Good example of why object-level and task-phase signals matter for OpenBot dataset detail pages.
A model hub link is a declaration. Files, loadability, evaluation, and deployment are scored separately.
Model decision scorecard
Use-case scores and evidence confidence are separate; Unknown is not treated as failure.
Code, weights, and checkpoints
UnknownArtifact availability is unknown.
Loading and training reproducibility
UnknownNo verified loading configuration is available.
Training data requirements
UsefulRequired signal categories are declared; exact tensor and action interfaces still need verification.
Evaluation evidence
UsefulEvaluation focus is declared, but metrics are not independently verified.
Deployment readiness
UnknownHardware, 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.
Observation / ego video
observation · Visual, proprioceptive, and action tokens over time
Language intent / task phase
language intent · Language instructions tied to particular objects · Instruction-to-object binding
Action / robot state
actions · robot state · Object-centric interaction traces · Visual, proprioceptive, and action tokens over time
Future state / dynamics
Object identity under scene shifts
Feedback / correction / failure
Needs success, failure, correction, or recovery signals to turn evaluation into better data.
Sim-real / embodiment metadata
robot state
Evaluation focus
- Object identity under scene shifts
- Instruction-to-object binding
- Robust manipulation across geometric perturbations
Missing critical loop signals
- Feedback / correction / failureNeeds success, failure, correction, or recovery signals to turn evaluation into better data.
Related catalog datasets
EgoTracks
Long-term object tracking in egocentric video
Exact action dimensions, control frequency, normalization, and camera mapping require interface verification.
EPIC-KITCHENS-100
Unscripted kitchen actions from wearable cameras
Exact action dimensions, control frequency, normalization, and camera mapping require interface verification.
EgoStation GoPro Pick-and-Place
GoPro first-person pick-and-place trajectories
Dataset license restricts commercial use.
OpenBot notes
- Good example of why object-level and task-phase signals matter for OpenBot dataset detail pages.
- Useful for connecting object tracking and manipulation datasets to WAM readiness.