Search papers, labs, and topics across Lattice.
3
1
6
8
Automated architecture search can enhance embodied agent performance, but it also reveals critical challenges that could hinder optimization.
Forget predefined maps: this VLN agent uses a learned, interactive world representation to achieve SOTA zero-shot performance and seamless sim-to-real transfer.
VLNVerse tackles the sim-to-real gap in vision-language navigation by providing a unified, large-scale benchmark with realistic physics simulation and full-kinematics embodied agents.
