Researchers Develop Domain-Specialized Large Language Models for Additive Manufacturing
A research team has created a suite of multimodal large language models fine-tuned specifically for additive manufacturing, built on open-weight base models including Gemma 3, Qwen 3, and Gemma 4. The models were trained using approximately 50 million tokens drawn from open-access additive manufacturing journal articles, employing domain adaptive pretraining and visual instruction tuning. The work demonstrates that relatively modest datasets can effectively specialize general-purpose LLMs for a technical engineering domain, with the adapted models achieving over 90% accuracy on an additive manufacturing benchmark.
Researchers have developed a collection of multimodal, domain-adapted large language models tailored to the field of additive manufacturing, using instruction-tuned variants of open-weight models — Gemma 3, Qwen 3, and Gemma 4 — as their foundation. The training dataset, comprising roughly 50 million tokens sourced from open-access additive manufacturing journal articles, was used for both domain adaptive pretraining and visual instruction tuning. Model performance was evaluated using the Additive-Manufacturing-Benchmark, a domain-specific evaluation suite compiled from published resources covering language and vision-based tasks. The adapted models achieved accuracies exceeding 90% on general additive manufacturing knowledge tasks, demonstrating meaningful gains over their general-purpose counterparts. The authors argue that their pipeline represents an accessible and reproducible method for specializing large language models to narrow technical domains without requiring massive proprietary datasets. The work was submitted to arXiv in March 2026 and updated in June 2026, and has not yet undergone formal peer review.
What's missing
Baseline comparisons against unmodified general-purpose models are not detailed in the abstract, making it difficult to quantify the precise improvement from domain adaptation. The generalizability of the 90%+ accuracy figure to real-world additive manufacturing tasks beyond the benchmark is unclear. Additionally, the dataset is restricted to open-access articles, which may introduce coverage bias relative to the full body of additive manufacturing literature.
What different sources said
- arXiv cs.LGCenter
Domain Adapted Large Language Models for Additive Manufacturing
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.