Universal Actions for Enhanced Embodied Foundation Models

J Zheng, J Li, D Liu, Y Zheng, Z Wang, Z Ou… - arxiv preprint arxiv …, 2025 - arxiv.org
Training on diverse, internet-scale data is a key factor in the success of recent large
foundation models. Yet, using the same recipe for building embodied agents has faced …

Imit Diff: Semantics Guided Diffusion Transformer with Dual Resolution Fusion for Imitation Learning

Y Dong, H Ge, Y Zeng, J Zhang, B Tian, G Tian… - arxiv preprint arxiv …, 2025 - arxiv.org
Visuomotor imitation learning enables embodied agents to effectively acquire manipulation
skills from video demonstrations and robot proprioception. However, as scene complexity …