Search papers, labs, and topics across Lattice.
4
0
4
24
Action QFormer boosts navigation success rates from 18.8% to 56.3% by intelligently reorganizing multimodal information under action supervision.
Policies trained on RynnWorld-Teleop's synthetic data achieve zero-shot transfer to real-world tasks, revolutionizing how we collect and utilize robotic training data.
RynnWorld-4D transforms robotic manipulation by co-producing future scene dynamics from a single RGB-D image, leading to unprecedented performance in dexterous tasks.
RoboDojo reveals that integrating simulation and real-world tasks can significantly enhance the evaluation of robot manipulation policies, bridging the gap between theoretical performance and practical deployment.
