Search papers, labs, and topics across Lattice.
3
0
5
Robustness in Open Vocabulary Object Detectors is driven more by image domain characteristics than by annotation methods, challenging existing assumptions about model training.
Bridging the aerial-to-ground gap just got easier: ProDiG leverages diffusion to synthesize intermediate views, enabling high-fidelity ground-level reconstruction from aerial imagery alone.
VLA-Thinker lets robots actively "look again" at their environment during long tasks, leading to a huge performance boost in complex manipulation.
