Chun-Ying Huang

model compression (2) adversarial robustness (1) knowledge editing (1) instruction following (1) model merging (1) responsible ai (1) safety alignment (1) layer-wise analysis (1) semantic similarity (1) semantic embedding (1) parameter-efficient fine-tuning (1) low-rank adaptation (1) model fine-tuning (1) task vector (1) model utility (1) parameter-efficient finetuning (1) sentence embedding (1) task arithmetic (1) large language model (1) command-line analysis (1)