Search papers, labs, and topics across Lattice.
Emory University
5
0
8
0
PriDyG slashes cumulative privacy costs by up to 99.9% while maintaining high utility in dynamic graph inference.
TIDE-MC achieves unprecedented efficiency in matrix completion, handling billion-scale datasets without running out of memory while delivering up to 11,647x speedup.
Just because your LLM has differential privacy doesn't mean attackers can't extract sensitive data from it.
Accurately simulating the snap-fit mechanics of interlocking bricks, BrickSim unlocks a new level of realism for robotic manipulation research involving complex assemblies.
Strategic recovery from failures is key to deploying robots for complex assembly tasks in the real world.
