3 papers
cs.AI2026
RadFusion: Towards Threshold-Controllable Radiology Report Generation
Ying Jin, Noel C. F. Codella, John Corring +3
Automated radiology report generation is advancing rapidly in response to the shortage of radiologists, yet unlike a perception model, existing generation models offer no control o…
cs.CL2026
RCEM: Robust Conversational Search EMbedder in Distributional Shift
Kilho Son, Paul Hsu, Cha Zhang +1
We propose RCEM, a Robust Conversational search EMbedder that is additionally equipped with LLM's query reformulation capability without losing base model's generalization. Unlike…
cs.CV2025
ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding
Xingyu Fu, Minqian Liu, Zhengyuan Yang +6
Structured image understanding, such as interpreting tables and charts, requires strategically refocusing across various structures and texts within an image, forming a reasoning s…