9 papers
HounsWorld: A Multimodal World Model for Hidden Patient-State Readout, Reconstruction, and Simulation
Yunhao Bai, Zhongwei Qiu, Guangyu Guo +5
Clinical intelligence requires estimating a patient's underlying condition from incomplete observations rather than learning isolated mappings from scans to answers. Volumetric med…
RadSight: Towards Perceptually Reliable Multimodal Radiology Image Understanding
Jianqin Liu, Weiwei Cao, Wanxing Chang +7
Medical multimodal large language models (MLLMs) are increasingly expected to perform complex image understanding tasks, yet their reliability is often compromised by frequent erro…
Super-Generalist: Towards Comprehensive and Accurate Medical Image Understanding via Generalist-Specialist Synergy
Shaoteng Zhang, Weiwei Cao, Wanxing Chang +9
Medical images require comprehensive and accurate interpretation to support the diagnosis of diverse clincial conditions. Recent vision-language generalist models offer broad task…
AtomiMed: Hierarchical Atomic Fact-Checking for Universal Clinical-Aware Medical Report Evaluation
Yuan Wang, Wanxing Chang, Songtao Jiang +8
Traditional metrics for Medical Report Generation (MRG) predominantly rely on surface-level n-gram overlap, which fails to capture clinical factual accuracy and often overlooks cat…
Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning
Pengyu Li, Zhitao Gao, Lingling Zhang +4
Unified multimodal models (UMMs) interleave generated ''visual thoughts'' (VTs) with text reasoning to improve spatial tasks. This incurs roughly an order-of-magnitude inference co…
Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed Tomography
Bowen Shi, Weiwei Cao, Ruifeng Yuan +5
Vision-language pre-training (VLP) holds great promise for general-purpose medical AI by leveraging radiology reports as rich textual supervision, yet existing methods struggle wit…