6 papers
Dynamic Decision Learning: Test-Time Evolution for Abnormality Grounding in Rare Diseases
Jun Li, Mingxuan Liu, Jiazhen Pan +4
Clinical abnormality grounding for rare diseases is often hindered by data scarcity, making supervised fine-tuning impractical and single-pass inference highly unstable. We propose…
Thinking Like a Clinician: A Cognitive AI Agent for Clinical Diagnosis via Panoramic Profiling and Adversarial Debate
Zhiqi Lv, Duofan Tu, Jun Li +4
The application of large language models (LLMs) in clinical decision support faces significant challenges of "tunnel vision" and diagnostic hallucinations present in their processi…
Learning to reason about rare diseases through retrieval-augmented agents
Ha Young Kim, Jun Li, Ana Beatriz Solana +4
Rare diseases represent the long tail of medical imaging, where AI models often fail due to the scarcity of representative training data. In clinical workflows, radiologists freque…
Knowledge to Sight: Reasoning over Visual Attributes via Knowledge Decomposition for Abnormality Grounding
Jun Li, Che Liu, Wenjia Bai +4
In this work, we address the problem of grounding abnormalities in medical images, where the goal is to localize clinical findings based on textual descriptions. While generalist V…
NOVA: A Benchmark for Anomaly Localization and Clinical Reasoning in Brain MRI
Cosmin I. Bercea, Jun Li, Philipp Raffler +12
In many real-world applications, deployed models encounter inputs that differ from the data seen during training. Out-of-distribution detection identifies whether an input stems fr…
Enhancing Abnormality Grounding for Vision Language Models with Knowledge Descriptions
Jun Li, Che Liu, Wenjia Bai +3
Visual Language Models (VLMs) have demonstrated impressive capabilities in visual grounding tasks. However, their effectiveness in the medical domain, particularly for abnormality…