Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
0
Across seven representative adapted baselines, Grounding2Route substantially outperforms existing methods in all metrics, and a substantial gap to human demonstrations remains, highlighting the difficulty of Map2Route and the considerable headroom for future progress.
Navigating with fewer than 8 VLM calls per episode, Goal2Pixel redefines efficiency in vision-language navigation tasks.
