Search papers, labs, and topics across Lattice.
University of Utah
3
0
5
Sampling the wrong data in differentially private queries can inflate error by 10x, but a new method slashes that overhead by sampling aggregation units instead of users.
Finally, a feed-forward method can generate realistic, simulation-ready garment patterns directly from single "in-the-wild" images, bypassing the need for multi-view inputs or expensive optimization.
Origami, the "Hello, World!" of physical intelligence, is now tractable: Learn2Fold uses LLMs and graph-structured world models to generate valid folding sequences from text.
