LGMar 23

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

arXiv:2603.2201756.4h-index: 44
AI Analysis

This provides an accessible method for specializing large language models to the additive manufacturing domain, though it is incremental as it adapts existing techniques to a new application area.

The researchers developed AdditiveLLM2, a multi-modal large language model specialized for additive manufacturing by adapting the Gemma 3 model with domain-specific pretraining and instruction tuning on a 50-million-token dataset. The model achieved over 90% accuracy on additive manufacturing knowledge tasks.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes