Zilong Wang

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Exploring Interpretability for Visual Prompt Tuning with Cross-layer Concepts

Reasoning-Driven Multimodal LLM for Domain Generalization

Joint Adaptation of Uni-modal Foundation Models for Multi-modal Alzheimer's Disease Diagnosis

Segmentation Helps Understanding: Mask-Infused Vision-Language Pre-training for 3D Medical Images

Is classification all you need for radiology report generation?

Stand on Two Shoulders: Dynamically Merging Tokens from General and Medical Experts

Learning Robust Representations for Medical Images via Unifying (Self-)Supervisions

Benchmark Dataset for Radiology Report Generation with Instructions and Contexts