For brain tumors, radiology reports provide essential imaging perspectives while pathology reports deliver microscopic confirmation, but each type of report typically requires domain experts to interpret separately. This separation can make it difficult to form a consistent basis for diagnosis and to reliably link findings to patient survival. Leveraging the integrative capabilities of large language models (LLMs), both sources can now be analyzed within a unified framework, reducing fragmentation and improving the accuracy of diagnostic classification and survival prediction.

To address this, a team led by Dr. Zhuoqi Ma (1^st author) and Dr. Zhicheng Jiao (corresponding) from the Department of Radiology at Brown University and Brown University Health developed a large language model (LLM)-based pipeline that integrates radiology and pathology reports within a unified framework. By leveraging the integrative capabilities of LLMs, both sources can be analyzed together and improving the accuracy of diagnostic classification and survival prediction. Their findings demonstrate the potential of this approach to enhance diagnostic reliability and support precision neuro-oncology.

The Global Burst Detection system, developed by Sandia and Los Alamos national laboratories, carries a suite of sensors and instruments capable of identifying signals from nuclear detonations and providing real-time information to the U.S. military and government. The final system in the current block of eight systems launched into space in May 2025. Meanwhile, the next series, scheduled for initial deployment in 2027, already has several units completed and ready to be integrated with host satellites.

In a pioneering study that explores the hidden carbon reservoirs of coastal ecosystems, researchers are quantifying the carbon stocks of macroalgal beds in the southwestern Atlantic Ocean. The study, titled "Carbon Stocks of Coastal Macroalgal Beds in the SW Atlantic," is led by Prof. Angelo Fraga Bernardino from the Departamento de Oceanografia at Universidade Federal Do Espírito Santo (UFES) in Vitória, Brazil. This research offers valuable insights into the role of macroalgal beds in carbon sequestration, highlighting their importance in marine protected areas.

Researchers have focussed on building a QA system which can answer query of user from building code and reduces the laborious traditional way of manual querying. One possible solution to build a robust QA system is to utilise the power of Retrieval Augmented Generation (RAG). Researchers have explored the potential of several retrieval methods and efficiency of Low Rank Adaptation (LoRA) to fine-tune Large Language Models (LLMs). Retrievers and LLMs are core component of a RAG system, and their performance affects overall performance of QA system.