Amir Gholami

model compression (8) neural network optimization (6) inference efficiency (4) mixed-precision quantization (4) model quantization (4) large language model (3) neural network quantization (3) scientific machine learning (2) hessian spectrum (2) batch normalization (2) hessian analysis (2) transformer architecture (2) neural network (2) knowledge distillation (2) data augmentation (2) partial differential equation (2) large batch training (2) object detection (1) curriculum learning (1) k-means clustering (1)