Aoming Liu

transfer learning (1) data augmentation (1) neural architecture search (1) visual reasoning (1) neural network optimization (1) sparse optimization (1) proximal gradient (1) convolutional neural network (1) recurrent neural network (1) bias-variance tradeoff (1) vision-language model (1) bi-level optimization (1) weight averaging (1) temporal expert (1) domain shift (1) differentiable search (1) synthetic dataset (1) temporal domain generalization (1) architecture optimization (1) data-efficient pretraining (1)