Jinjie Yuan

model compression (4) parameter-efficient fine-tuning (3) low-rank adaptation (2) low-rank adapter (2) neural architecture search (2) large language model (2) inference efficiency (1) retrieval-augmented generation (1) low-precision quantization (1) cross-domain generalization (1) schema linking (1) database schema (1) graph neural network (1) adaptive selection (1) test-time compute (1) weight-sharing super-network (1) selective structured state space model (1) structure-aware aggregation (1) model merging (1) sparse model (1)