Notable publication: ALPINE – Greener Language Models for Code

In “An Adaptive Language-Agnostic Pruning Method for Greener Language Models for Code,” Mootez Saad, José Antonio Hernández López, Boqi Chen, Dániel Varró, and Tushar Sharma present ALPINE, a pruning technique designed to make language models for code significantly more energy- and compute-efficient.

ALPINE adaptively prunes model parameters in a programming-language-agnostic fashion while preserving task performance, offering a practical path toward greener code intelligence systems. The work appears at ACM Foundations of Software Engineering (FSE), a **CORE A*–ranked** software engineering venue.

Read the paper: https://doi.org/10.1145/3715773