🔄 In a Training Loop

Sebastian Stapf

sebastian-stapf

9 3

·

AI & ML interests

None yet

Recent Activity

liked a Space 2 days ago

sebastian-stapf/worldtasks-blinded-human-eval

updated a Space 2 days ago

sebastian-stapf/worldtasks-blinded-human-eval

published a Space 4 days ago

sebastian-stapf/worldtasks-blinded-human-eval

View all activity

Organizations

Papers 6

arxiv:2606.12072

arxiv:2605.18813

arxiv:2602.20731

arxiv:2510.24448

spaces 2

WorldTasks Blinded Human Evaluation

Blinded pairwise video-rating interface for WorldTasks

WorldTasks Human Evaluation

Rate and compare paired videos for task performance

models 0

None public yet

datasets 1

sebastian-stapf/WorldTasks

Viewer • Updated Jun 11 • 18.3k • 223 • 2