papers

Publications (8)

cs.CV2025

Boltzmann Attention Sampling for Image Analysis with Small Objects

Theodore Zhao, Sid Kiblawi, Naoto Usuyama +4

Detecting and segmenting small objects, such as lung nodules and tumor lesions, remains a critical challenge in image analysis. These objects often occupy less than 0.1% of an imag…

cs.CV2026

Scaling medical imaging report generation with multimodal reinforcement learning

Qianchu Liu, Sheng Zhang, Guanghui Qin +11

Frontier models have demonstrated remarkable capabilities in understanding and reasoning with natural-language text, but they still exhibit major competency gaps in multimodal unde…

cs.CL2022

Towards Structuring Real-World Data at Scale: Deep Learning for Extracting Key Oncology Information from Clinical Text with Patient-Level Supervision

Sam Preston, Mu Wei, Rajesh Rao +11

Objective: The majority of detailed patient information in real-world data (RWD) is only consistently available in free-text clinical documents. Manual curation is expensive and ti…

cs.LG2025

Demo: Healthcare Agent Orchestrator (HAO) for Patient Summarization in Molecular Tumor Boards

Matthias Blondeel, Noel Codella, Sam Preston +9

Molecular Tumor Boards (MTBs) are multidisciplinary forums where oncology specialists collaboratively assess complex patient cases to determine optimal treatment strategies. A cent…

cs.CL2025

Universal Abstraction: Harnessing Frontier Models to Structure Real-World Data at Scale

Cliff Wong, Sam Preston, Qianchu Liu +22

A significant fraction of real-world patient information resides in unstructured clinical text. Medical abstraction extracts and normalizes key structured attributes from free-text…

cs.AI2025

X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains

Qianchu Liu, Sheng Zhang, Guanghui Qin +9

Recent proprietary models (e.g., o3) have begun to demonstrate strong multimodal reasoning capabilities. Yet, most existing open-source research concentrates on training text-only…

cs.CV2025

BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs

Sheng Zhang, Yanbo Xu, Naoto Usuyama +21

Biomedical data is inherently multimodal, comprising physical measurements and natural language narratives. A generalist biomedical AI model needs to simultaneously process differe…

cs.LG2025

CancerGUIDE: Cancer Guideline Understanding via Internal Disagreement Estimation

Alyssa Unell, Noel C. F. Codella, Sam Preston +13

The National Comprehensive Cancer Network (NCCN) provides evidence-based guidelines for cancer treatment. Translating complex patient presentations into guideline-compliant treatme…