Maria Valentini — accepted AI-conference papers

2024

DeliGrasp: Inferring Object Properties with LLMs for Adaptive Grasp Policies

William Xie, Maria Valentini, Jensen Lavering, Nikolaus Correll

CoRL 2024poster

Large language models (LLMs) can provide rich physical descriptions of most worldly objects, allowing robots to achieve more informed and capable grasping. We leverage LLMs' common sense physical reasoning and code-writing abilities to infer an object's physical characteristics-mass $m$, friction co…

Cited by 4 Source ↗code ↗Scholar ↗

2023

On the Automatic Generation and Simplification of Children's Stories

Maria Valentini, Jennifer Weber, Jesus Salcido, Téa Wright, Eliana Colunga, Katharina von der Wense

EMNLP 2023long main

With recent advances in large language models (LLMs), the concept of automatically generating children’s educational materials has become increasingly realistic. Working toward the goal of age-appropriate simplicity in generated educational texts, we first examine the ability of several popular LLMs…

Cited by 0 Source ↗Scholar ↗