Linxin Yang

From Sequential to Parallel: Reformulating Dynamic Programming as GPU Kernels for Large-Scale Stochastic Combinatorial Optimization

Feature Augmentation of GNNs for ILPs: Local Uniqueness Suffices

QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks

An Efficient Unsupervised Framework for Convex Quadratic Programs via Deep Unrolling