Yuxiong He

model compression (8) large language model (5) knowledge distillation (5) mixture of expert (3) inference optimization (3) neural network optimization (3) weight quantization (3) efficient computing (3) batch size (2) transformer model (2) efficient training (2) retrieval-augmented generation (2) training efficiency (2) post-training quantization (2) sparse model (2) deep learning (1) natural language understanding (1) curriculum learning (1) model pretraining (1) multimodal learning (1)