Search papers, labs, and topics across Lattice.
3
0
4
4
Teaching VLMs to "look back" and "look ahead" with lightweight spatial reasoning tasks unlocks surprisingly strong navigation performance.
Image-goal navigation gets a boost from hierarchical reasoning, using vision-language models for high-level planning and online RL for low-level execution, significantly reducing wandering and improving success in complex environments.
Ditch language descriptions: this new driving model leverages dense 3D geometry for superior autonomous driving performance and cross-camera generalization.
