← Search

Park Yu Been

1 accepted papers

2026

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

ICLR 2026poster

Large language models leverage internet-scale text data, yet embodied AI remains constrained by the prohibitive costs of physical trajectory collection. Desktop environments---particularly gaming---offer a compelling alternative: they provide rich sensorimotor interactions at scale while maintaining…

Cited by 0SourcecodeScholar