Huichi Zhou

large language model (3) adversarial attack (2) text classification (2) semantic consistency (1) diffusion model (1) adversarial defense (1) vision-language model (1) model fine-tuning (1) multimodal reasoning (1) radiology report generation (1) fine-grained evaluation (1) small language model (1) word-level attack (1) format following (1) json format (1) verifiable dataset (1) iterative denoising (1) llm-based evaluation (1) validity evaluation (1) medical report evaluation (1)