I'm excited to co-supervise Jacob Cumming's PhD in Maths at the University of Melbourne. He's studying branching processes with applications to New Testament textual criticism. More here: robturnbull.com

I’m working with Dr Peta Taylor (Lecturer in Animal Science at unimelb) on the welfare of chickens in transport. Peta will present some of our results at the Australian Poultry Science Symposium in Sydney on Wednesday.

Yesterday I had my book launch and I was honoured to have Emily Tour, Michael F. Bird, Alexander Treiger, Stephen Carlson and Joey McCollum speak about the book. Here is a playlist of what they had to say: youtube.com/playlist?list=…

Excited to share Terrier 🧬✨🐶 — our new AI model to classify repetitive DNA. DNA repeats make up huge parts of genomes and play a key role in evolution, but are notoriously hard to classify. Preprint just released: doi.org/10.48550/arXiv…

I've got a little python package called llmloader to load LLMs in LangChain just by the model name. I just updated it to include Mistral AI : github.com/rbturnbull/llm…

Our paper "Potnia: A Python library for the conversion of transliterated ancient texts to Unicode" is now published in JOSS 👉 doi.org/10.21105/joss.… Potnia currently supports Linear A, Linear B, Arabic, and Hittite cuneiform—with more Anatolian languages on the way

Mammograms are painful and only 2D. CT could be better—but needs high dosage to reduce noise. Using phase-contrast and AI denoising, we cut the dose 16× with no loss of image quality. We continue to work towards safe, 3D breast cancer screening. Preprint doi.org/10.48550/arXiv…

Looking forward to giving guest lectures on LLMs for the Data Journalism course at the University of Melbourne over the next couple of days

🎉 Delighted to join Prof Christina Kreinecker and the KU Leuven team on the ERC BICROSS project, working on multilingual manuscripts using AI. Announcement: theo.kuleuven.be/en/research/re…

Just out in BioScience: our new article on Hespi, an LLM-powered pipeline for extracting information from herbarium sheets. 🌿 doi.org/10.1093/biosci… Watch this space for lots more developments in this area!

📣 Just published an article in the University of Melbourne's Pursuit about my research using phylogenetics to uncover the history of Arabic Gospel manuscripts: pursuit.unimelb.edu.au/articles/scien…

Just finished giving a seminar on writing tests for Python. Here are some memes I made for it — plus a Python package showcasing pytest, coverage and Github Actions: github.com/rbturnbull/pyt…

🚀 Just out: our article on Hespi, an LLM pipeline for extracting information from herbarium specimen sheets, is the cover story of BioScience's August issue 🌿 doi.org/10.1093/biosci…

Our article on Hespi, an AI pipeline for extracting information from herbarium specimen sheets, is now published in The Conversation: theconversation.com/botanical-time…

📢 Our new paper is out in Briefings in Bioinformatics. Much of DNA is made of “repeats” — hard-to-classify sequences that shape genomes. We introduce Terrier 🐾, an AI tool that classifies repeats across diverse species👉 doi.org/10.1093/bib/bb…

Great to be part of the Computing and Information Systems poster session today at Melbourne Connect Innovation Week. The poster for our software to read herbarium specimen sheets is here: raw.githubusercontent.com/rbturnbull/hes…

I'm excited to work with Museums Victoria to digitise their collection of graptolite fossils: unimelb.edu.au/newsroom/news/…

New paper out. 'Themeda: Predicting Land Cover Change Using Deep Learning' We trained AI on 33 years of satellite data to forecast land cover across northern Australia’s savannas. spj.science.org/doi/abs/10.341…

I’m working with Joey McCollum on an article about an Arabic translation of Paul’s letters. It differs strikingly from the Majority/Byzantine text. Even from the small Text und Textwert sample in Ephesians, it's clear the Arabic preserves a distinctive textual lineage.

Algae drive the Earth’s oxygen production and marine food chains. My PhD student Andy’s preprint introduces ChloroScan, a tool that recovers plastid genomes from metagenomic data to uncover hidden biodiversity in environmental samples: arxiv.org/abs/2510.10950