Search papers, labs, and topics across Lattice.
Robot-synthesized data (abbreviated Ego
3
0
4
4
Joint pretraining on Ego2Robot-synthesized data boosts robot generalization, achieving unprecedented scale and diversity in training datasets.
APT achieves substantial improvements in instruction generalization for VLA models by effectively decoupling language and action learning, addressing a critical data imbalance issue.
One model to control them all: Qwen-VLA achieves impressive zero-shot generalization across diverse robotic tasks and embodiments by unifying vision-language-action modeling.
