Search papers, labs, and topics across Lattice.
2
4
4
19
Designing resilient networks under uncertainty is now more tractable thanks to new scalable robust optimization methods and a hide-and-seek game formulation.
Aligning LLMs to multiple objectives just got 1000x faster: PAMA reduces the computational complexity of multi-objective RLHF from quadratic to linear, enabling practical Pareto optimization.
