4 papers
SD-GRPO: Verifiable Segment Decomposition for Long-Form Vision-Language Generation
Hyunwoong Kim, Seongeun Lee, Hannah Yun +2
Group Relative Policy Optimization (GRPO) and its variants, originally developed for Large Language Models (LLMs), have recently been applied to Multimodal LLMs and produced strong…
GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations
Jonggwon Park, Seongeun Lee, Junhyun Park +6
Vision-language models (VLMs) for radiology have emerged as a scalable paradigm by leveraging image-report pairs naturally produced in clinical workflows. However, this pairing rev…
RA-RRG: Multimodal Retrieval-Augmented Radiology Report Generation with Key Phrase Extraction
Jonggwon Park, Byungmu Yoon, Soobum Kim +1
Automated radiology report generation (RRG) holds potential to reduce the workload of radiologists, and recent advances in multimodal large language models (MLLMs) have enabled mul…
RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Chest X-ray with Zero-Shot Multi-Task Capability
Jonggwon Park, Byungmu Yoon, Soobum Kim +1
Recent advancements in multimodal models have significantly improved vision-language (VL) alignment in radiology. However, existing approaches struggle to effectively utilize compl…