Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation Paper β’ 2504.17025 β’ Published Apr 23 β’ 16
PROMPTEVALS: A Dataset of Assertions and Guardrails for Custom Production Large Language Model Pipelines Paper β’ 2504.14738 β’ Published Apr 20 β’ 5
Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction Paper β’ 2504.15266 β’ Published Apr 21 β’ 3
SilVar-Med: A Speech-Driven Visual Language Model for Explainable Abnormality Detection in Medical Imaging Paper β’ 2504.10642 β’ Published Apr 14 β’ 2