Repurposing Foundation Model for Generalizable Medical Time Series Classification

Posted by dbos Berkeley

Kavli Affiliate: Xiang Zhang | First 5 Authors: Nan Huang, Haishuai Wang, Zihuai He, Marinka Zitnik, Xiang Zhang | Summary: Medical time series (MedTS) classification is critical for a wide range of healthcare applications such as Alzheimer’s Disease diagnosis. However, its real-world deployment is severely challenged by poor generalizability due to inter- and intra-dataset heterogeneity […]


Continue.. Repurposing Foundation Model for Generalizable Medical Time Series Classification

GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data

Posted by dbos Tokyo

Kavli Affiliate: Jia Liu | First 5 Authors: Jifan Zhang, Ziyue Luo, Jia Liu, Ness Shroff, Robert Nowak | Summary: Large language models require vast amounts of high-quality training data, but effective filtering of web-scale datasets remains a significant challenge. This paper demonstrates that GPT-4o is remarkably effective at identifying high-quality training data, but its […]


Continue.. GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data