Cua
@trycua
Your computers, shared by your team and its agents
Joined January 2025
2.4K Following 28.1K Followers
1/ Today we're introducing Cua-S1-4B-0.2, the first multimodal decision model trained with RLOO on live computer-use tasks, using task-completion rewards.
Text and multimodal adapters are available under Apache-2.0:
Show more
