Search papers, labs, and topics across Lattice.
Affiliation:
4
0
5
8
Robots can now intelligently choose camera angles to answer questions by predicting the utility of unseen views, bypassing costly real-time rendering.
CapFrame achieves superior viewpoint alignment with textual instructions, outperforming traditional heuristic methods in 3D scene rendering.
Existing Video REC models falter dramatically when faced with the complexities of long-form egocentric videos, revealing a critical gap in current methodologies.
NavWAM turns visual foresight into executable robot actions, outperforming traditional planning methods in real-world navigation scenarios.
