D2E - a open-world-agents Collection

open-world-agents 's Collections

D2E

updated 6 days ago

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

Paper • 2510.05684 • Published Oct 7, 2025 • 143
Running on Zero

Generalist IDM

📊

Process gameplay videos to predict keyboard and mouse actions
open-world-agents/Generalist-IDM-1B

Image-Text-to-Text • 0.9B • Updated Jan 15 • 1.84k • 3
open-world-agents/D2E-480p

Viewer • Updated 5 days ago • 460 • 6.85k • 1
open-world-agents/D2E-Original

Viewer • Updated 5 days ago • 460 • 3.51k • 2