-
D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI
Paper • 2510.05684 • Published • 145 -
Generalist IDM
📊Process gameplay videos to predict keyboard and mouse actions
-
open-world-agents/Generalist-IDM-1B
Image-Text-to-Text • 0.9B • Updated • 5.59k • 3 -
open-world-agents/D2E-480p
Viewer • Updated • 460 • 5.99k • 1
open-world-agents
non-profit
AI & ML interests
None defined yet.
Recent Activity
-
D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI
Paper • 2510.05684 • Published • 145 -
Generalist IDM
📊Process gameplay videos to predict keyboard and mouse actions
-
open-world-agents/Generalist-IDM-1B
Image-Text-to-Text • 0.9B • Updated • 5.59k • 3 -
open-world-agents/D2E-480p
Viewer • Updated • 460 • 5.99k • 1
datasets 9
open-world-agents/D2E-Original
Viewer • Updated • 460 • 2.48k • 2
open-world-agents/D2E-480p
Viewer • Updated • 460 • 5.99k • 1
open-world-agents/OSTask-demo
Viewer • Updated • 5 • 80
open-world-agents/example-pubg-battleground
Viewer • Updated • 1 • 47
open-world-agents/vpt-owamcap
Updated • 12.8k • 5
open-world-agents/example_dataset2
Viewer • Updated • 1 • 78
open-world-agents/example-djmax
Viewer • Updated • 1 • 14
open-world-agents/example-aimlab
Viewer • Updated • 1 • 15
open-world-agents/example_dataset
Viewer • Updated • 1 • 678