Search papers, labs, and topics across Lattice.
4
0
8
7
Automated preference-objective discovery can dramatically enhance the efficiency and performance of neural combinatorial optimization, outperforming traditional methods.
EvoPINN autonomously discovers new algorithms for physics-informed neural networks, achieving significant performance improvements while ensuring scientific validity.
RefineEvo transforms heuristic design from static trial-and-error into a dynamic, experience-driven process that significantly boosts solution quality and efficiency.
Ditch diffusion models: MeanFlow policies offer a faster, leaner path to high-performing reinforcement learning agents.
