Search papers, labs, and topics across Lattice.
4
0
5
9
A single 500-hour visual-tactile dataset boosts zero-shot contact prediction from 13% to 38% IoU and quadruples robot manipulation success rates, proving scale and consistency are paramount for embodied learning.
Gripper-aware learning can drastically enhance robotic manipulation, with GVLA outperforming existing models in adaptability and performance across diverse tasks.
Surgeons can now access real-time insights from surgical videos with over 100x faster response times, thanks to a novel generative retrieval framework.
Current robotic grasping methods struggle, with success rates under 70% in complex scenarios that demand reasoning and semantic understanding.
