Xiangzheng Zhang

large language model (4) supervised fine-tuning (3) adversarial learning (1) model robustness (1) mathematical reasoning (1) model distillation (1) multi-modal learning (1) vision language model (1) visual reasoning (1) instruction following (1) safety alignment (1) generalization ability (1) diffusion model (1) model training (1) language model (1) chain-of-thought reasoning (1) curriculum learning (1) jailbreak attack (1) multi-turn dialogue (1) benchmark evaluation (1)