AdditiveLLM2: A Multi-modal Large Language Model for Additive Manufacturing

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pak, Peter, Farimani, Amir Barati
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908907049320448
author Pak, Peter
Farimani, Amir Barati
author_facet Pak, Peter
Farimani, Amir Barati
contents This work presents AdditiveLLM2 a multi-modal, domain adapted large language model built upon the instruction tuned variant of the Gemma 3 model using a relatively small dataset of around 50 million tokens. The dataset (AdditiveLLM2-OA) consists of open-access additive manufacturing journal articles with data extracted for the domain adaptive pretraining and visual instruction tuning processes. Various stages of the developed model are evaluated with the Additive-Manufacturing-Benchmark which consists of additive manufacturing domain specific tasks compiled published resources. AdditiveLLM2 exhibits proficiency in both language and vision based tasks, achieving accuracies upwards of 90% in general additive manufacturing knowledge. This domain adaptive pretraining and instruction tuning strategy outline an accessible specialization method for large language models to a domain such as additive manufacturing.
format Preprint
id arxiv_https___arxiv_org_abs_2603_22017
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AdditiveLLM2: A Multi-modal Large Language Model for Additive Manufacturing
Pak, Peter
Farimani, Amir Barati
Machine Learning
This work presents AdditiveLLM2 a multi-modal, domain adapted large language model built upon the instruction tuned variant of the Gemma 3 model using a relatively small dataset of around 50 million tokens. The dataset (AdditiveLLM2-OA) consists of open-access additive manufacturing journal articles with data extracted for the domain adaptive pretraining and visual instruction tuning processes. Various stages of the developed model are evaluated with the Additive-Manufacturing-Benchmark which consists of additive manufacturing domain specific tasks compiled published resources. AdditiveLLM2 exhibits proficiency in both language and vision based tasks, achieving accuracies upwards of 90% in general additive manufacturing knowledge. This domain adaptive pretraining and instruction tuning strategy outline an accessible specialization method for large language models to a domain such as additive manufacturing.
title AdditiveLLM2: A Multi-modal Large Language Model for Additive Manufacturing
topic Machine Learning
url https://arxiv.org/abs/2603.22017