Juan Pablo Munoz

model compression (3) neural architecture search (3) parameter efficient fine-tuning (2) federated learning (2) weight sharing (2) parameter-efficient fine-tuning (2) low-rank adaptation (2) low-rank adapter (2) large language model (2) collaborative learning (1) sparse model (1) reward model (1) foundation model (1) weight-sharing super-network (1) transformer compression (1) model architecture (1) inference optimization (1) inference efficiency (1) retrieval-augmented generation (1) hidden representation (1)