Qingjiang Shi

DogRot: Taming Highly Ill-Conditioned Sensing Matrix in Sparse Signal Recovery by Random Gaussian Rotator

Feature Augmentation of GNNs for ILPs: Local Uniqueness Suffices

ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut Problems

When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approach

ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut Problems

Towards Explaining the Power of Constant-depth Graph Neural Networks for Structured Linear Programming

On Representing Convex Quadratically Constrained Quadratic Programs via Graph Neural Networks

FedQLoRA: Federated Quantization-Aware LoRA for Large Language Models