New Resource
Research on new resources focuses on expanding and improving datasets and tools for various natural language processing (NLP) tasks, particularly in low-resource languages and specialized domains like agriculture and banking. Current efforts involve developing large language models (LLMs), knowledge graphs, and benchmark datasets, often incorporating techniques like retrieval augmented generation (RAG) and parameter-efficient fine-tuning to enhance model performance and resource efficiency. These advancements are crucial for improving the accessibility and accuracy of NLP applications across diverse fields, facilitating scientific discovery and enabling more inclusive technological solutions.
Papers
FedHiSyn: A Hierarchical Synchronous Federated Learning Framework for Resource and Data Heterogeneity
Guanghao Li, Yue Hu, Miao Zhang, Ji Liu, Quanjun Yin, Yong Peng, Dejing Dou
covEcho Resource constrained lung ultrasound image analysis tool for faster triaging and active learning
Jinu Joseph, Mahesh Raveendranatha Panicker, Yale Tung Chen, Kesavadas Chandrasekharan, Vimal Chacko Mondy, Anoop Ayyappan, Jineesh Valakkada, Kiran Vishnu Narayan