Tag
This paper introduces MagBridge-Battery, a synthetic dataset of 6,760 magnetic-field signatures for Li-ion battery state-of-health diagnostics, combining real magnetic morphology with real degradation labels to bridge the gap in public magnetic-sensing battery data.
This paper introduces a framework for synthesizing long-term medical dialogue datasets using LLMs, and creates MediLongChat with three benchmark tasks to evaluate healthcare agents' memory and reasoning capabilities. Experiments show that even state-of-the-art LLMs struggle with these tasks.