Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds Paper • 2511.08892 • Published 9 days ago • 173
D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI Paper • 2510.05684 • Published Oct 7 • 139
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery Paper • 2510.15869 • Published Oct 17 • 44
InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy Paper • 2510.13778 • Published Oct 15 • 16