← Search

Yingjie Han

2 accepted papers

2025

CmEAA: Cross-modal Enhancement and Alignment Adapter for Radiology Report Generation

COLING 2025main

Automatic radiology report generation is pivotal in reducing the workload of radiologists, while simultaneously improving diagnostic accuracy and operational efficiency. Current methods face significant challenges, including the effective alignment of medical visual features with textual features an…

2025

JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling

EMNLP 2025

Text-to-SQL, which maps natural language to SQL queries, has benefited greatly from recent advances in Large Language Models (LLMs). While LLMs offer various paradigms for this task, including prompting and supervised fine-tuning (SFT), SFT approaches still face challenges such as complex multi-stag