Kyle Wiggers

Ai2Comms

·

AI & ML interests

None yet

Recent Activity

published an article 1 day ago

ToyBlocks: A controlled world for robot learning and evaluation

published an article 4 days ago

StateBench: Testing how language models track state changes over long documents

published a dataset 4 days ago

allenai/state-bench

View all activity

Organizations

Articles 21

Article

6

ToyBlocks: A controlled world for robot learning and evaluation

Article

17

StateBench: Testing how language models track state changes over long documents

View all Articles

models 0

None public yet

datasets 0

None public yet