myheart521

myheart521/WAMProbe

Counterfactual evaluation for World Action Models

1 stars 0 forks 1 watchers Python Apache License 2.0
benchmark counterfactual-evaluation embodied-ai evaluation python robotics vision-language-action world-action-model world-model
View on GitHub Website
5 Open Issues Need Help Last updated: Jul 16, 2026

Open Issues Need Help

View All on GitHub
Audit a public WAM that exposes action-conditioned candidate futures 21 days ago
help wanted area:adapter needs-rfc
myheart521/WAMProbe
1

Counterfactual evaluation for World Action Models

Python
#benchmark#counterfactual-evaluation#embodied-ai#evaluation#python#robotics#vision-language-action#world-action-model#world-model
Expand LIBERO-CF-Mini initial-state coverage 21 days ago
help wanted area:benchmark
myheart521/WAMProbe
1

Counterfactual evaluation for World Action Models

Python
#benchmark#counterfactual-evaluation#embodied-ai#evaluation#python#robotics#vision-language-action#world-action-model#world-model
Add a troubleshooting table to the custom adapter guide 21 days ago
documentation help wanted good first issue area:adapter
myheart521/WAMProbe
1

Counterfactual evaluation for World Action Models

Python
#benchmark#counterfactual-evaluation#embodied-ai#evaluation#python#robotics#vision-language-action#world-action-model#world-model
Add malformed-output tests to the custom adapter starter 21 days ago
help wanted good first issue area:adapter
myheart521/WAMProbe
1

Counterfactual evaluation for World Action Models

Python
#benchmark#counterfactual-evaluation#embodied-ai#evaluation#python#robotics#vision-language-action#world-action-model#world-model
Design the Occluded-Object memory diagnostic RFC 21 days ago
help wanted needs-rfc area:benchmark
myheart521/WAMProbe
1

Counterfactual evaluation for World Action Models

Python
#benchmark#counterfactual-evaluation#embodied-ai#evaluation#python#robotics#vision-language-action#world-action-model#world-model