Search papers, labs, and topics across Lattice.
4
0
7
5
ACE-Data-0 reveals that existing models struggle significantly with complex interactions, exposing critical gaps in embodied AI performance.
Current video generation models struggle with law-grounded reasoning, with the best achieving only 47% on the new Apple-PI benchmark.
Sampling-based trajectory optimization can escape local minima faster by explicitly modeling trajectory uncertainty and enforcing distributional separation.
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.
