Search papers, labs, and topics across Lattice.
6
0
5
10
ACE-Data-0 reveals that existing models struggle significantly with complex interactions, exposing critical gaps in embodied AI performance.
Current vision-language models fail to achieve embodied self-awareness, with none surpassing a 16.8% success rate in real-world interaction tasks.
The data pyramid framework reveals how the interplay of diverse data sources can unlock new capabilities in embodied agents, highlighting critical gaps in current methodologies.
IGGT4D achieves unprecedented consistency in geometry-instance representation from streaming video, outperforming existing methods in dynamic scene understanding.
Training on a new multi-object dataset with explicit modeling of grasp offsets and pre-grasp configurations enables an end-to-end network to achieve significantly improved dexterous grasping performance in simulation and on a real robot.
Finally, a method exists to create 3D human-scene interaction models from casual captures that are stable enough for use in physics simulations and deployment on real-world robots.
