Search papers, labs, and topics across Lattice.
4
0
5
7
Continuous alignment of text and visual representations in DINOde leads to significant performance gains in open-vocabulary semantic segmentation, outperforming traditional methods.
Skill Conflict can severely hinder robot navigation performance, but Disjoint Parameter Training offers a solution that enhances both prediction and planning in crowded environments.
Grounding motion predictions in 3D spatial context and language leads to significantly more accurate and coherent forecasts of human actions.
RAHA achieves superior cross-modal retrieval performance by leveraging hyperbolic geometry to better capture the low-dimensional semantics of image-text pairs.
