Search papers, labs, and topics across Lattice.
6
0
5
Qwen-RobotManip achieves a 20% relative improvement over the previous state-of-the-art in robotic manipulation, showcasing unprecedented generalization capabilities from diverse, open-source datasets.
Qwen-RobotNav redefines navigation by allowing real-time reconfiguration of strategies, achieving unprecedented flexibility and performance across diverse tasks.
Language-driven video generation in Qwen-RobotWorld achieves unprecedented accuracy in predicting robotic actions, outperforming existing models across key benchmarks.
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.
Forget painstakingly tuning force magnitudes for sim-to-real transfer of contact-rich tasks; this work shows that learning just the *direction* of contact forces unlocks surprisingly robust performance.
