🏢 Northwestern Polytechnical University

Meta-Exploiting Frequency Prior enhances cross-domain few-shot learning by leveraging image frequency decomposition and consistency priors to improve model generalization and efficiency.

Homogenized SGD reveals heavy-tailed neural network parameters, offering quantifiable bounds on tail-index and showcasing the interplay between optimization hyperparameters and model generalization.

AI-powered drug interaction prediction gets a boost! CSSE-DDI uses neural architecture search to customize subgraph selection and encoding, resulting in superior accuracy and efficiency compared to e…

AlterMOMA: A novel pruning framework significantly improves camera-LiDAR fusion models by identifying and removing redundant parameters through an alternative modality masking technique, achieving sta…

3DFMNet: A novel two-stage network for multi-instance point cloud registration, achieving state-of-the-art accuracy by focusing on object centers first and then performing pairwise registration.