3 accepted papers
Large language models (LLMs) are widely applied to data analytics over documents, yet direct reasoning over long, noisy documents remains brittle and error-prone. Hence, we study document question answering (QA) that consolidates dispersed evidence into a structured output (e.g., a table, graph, or…
Fine-tuning large language models (LLMs) is compute-intensive and error-prone: model performance depends sensitively on data quality and hyperparameter choices, and naïve runs can even degrade model performance. This raises a fundamental question: Can we predict fine-tuning performance before traini…
Organoids are a class of popular three-dimensional in vitro models that recapitulate the structural, genetic, and functional characteristics of their native tissues, offering powerful tools for drug screening and precision medicine. While recent advances have integrated robotic automation into organ