Xindi Li — accepted AI-conference papers

2025

Learnable Retrieval Enhanced Visual-Text Alignment and Fusion for Radiology Report Generation

Qin Zhou, Guoyan Liang, Xindi Li, Jingyuan Chen, Zhe Wang, Chang Yao +1

ICCV 2025poster

Automated radiology report generation is essential for improving diagnostic efficiency and reducing the workload of medical professionals. However, existing methods face significant challenges, such as disease class imbalance and insufficient cross-modal fusion. To address these issues, we propose t…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

TWIST: Text-encoder Weight-editing for Inserting Secret Trojans in Text-to-Image Models

Xindi Li, Zhe Liu, Tong Zhang, Jiahao Chen, Qingming Li, Jinbao Li +1

ACL 2025long

Text-to-image (T2I) models excel at generating high-quality images from text via powerful text encoders but training these encoders demands substantial computational resources. Consequently, many users seek pre-trained text encoders from model plugin-sharing platforms like Civitai and Hugging Face,…

Cited by 0 Source ↗PDF ↗Scholar ↗