Tianyu Dong

large language model (2) machine translation (2) quality estimation (1) neural network optimization (1) multilingual machine translation (1) instruction tuning (1) low-resource language (1) parameter-efficient fine-tuning (1) low-rank adaptation (1) mixture of expert (1) continual pre-training (1) parametric knowledge (1) language-aware learning (1) semantic fidelity (1) reinforcement learning with verifiable reward (1) cross-cultural entity translation (1) knowledge distillation (1) partial hallucination (1) preference optimization (1)