Skip to content
University of Guelph · Vector Institute

Graham Taylor

Professor and Canada Research Chair in Machine Learning. Developing fundamental deep learning methods, with biodiversity science as both motivation and a sandbox for methods at scale.

Photo of Graham Taylor

I lead the Machine Learning Research Group at the University of Guelph. We develop deep learning methods spanning generative modelling, multimodal representation learning across vision, DNA, and language, graph neural networks, and uncertainty quantification — with recurring interests in learning under limited supervision, AI for science, and the design of LLM-based agents as collaborators in research workflows.

Much of this research is motivated by the challenge of monitoring and preserving Earth's biodiversity. With biologists and ecologists, we build large-scale multimodal datasets and foundation models that integrate images, DNA barcodes, and text. I am a co-PI of BIOSCAN, a global initiative monitoring multicellular life at planetary scale, and contribute as senior personnel to the NSF/NSERC-funded Artificial Intelligence and Biodiversity Change (ABC) Global Center, an international team developing AI for ecosystem monitoring.

I co-direct the Centre for Advancing Responsible and Ethical AI (CARE-AI) at Guelph, am a Canada CIFAR AI Chair and faculty member at the Vector Institute, and serve as Academic Director of Next AI, a non-profit accelerator for AI-focused entrepreneurs.

News

Aug 2026 Our continental-scale ground beetle dataset, with high-resolution images and validated morphological trait measurements, is accepted to Scientific Data. Congratulations Scott Lowe, Iuliia Eyriay, and co-authors!
Jul 2026 "An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Encoders" is accepted to Transactions on Machine Learning Research. Congratulations Scott Lowe!
May 2026 Our work on hierarchy-aware uncertainty estimation for black-box LLM taxonomic reasoning appeared at the 39th Canadian Conference on Artificial Intelligence. Congratulations Shuting Xie and Nate Lesperance!
May 2026 Our position paper on tracking the cumulative footprint of open-source model derivatives is accepted to the ICML 2026 Position Paper Track. Congratulations Shaina Raza, Iuliia Eyriay, Nate Lesperance, and co-authors!
Apr 2026 On 2026-04-29 I received the inaugural Ontario Centre of Innovation Educator Innovation & Entrepreneurship Award ($20,000) at DiscoveryX.
All news →

Research Highlights

A multi-modal dataset for insect biodiversity with imagery and DNA at the trap and individual level
Johanna Orsholm, John Quinto, Hannu Autto, Gaia Banelyte, Nicolas Chazot, Jeremy deWaard, Stephanie deWaard, Arielle Farrell, Brendan Furneaux, Bess Hardwick, Nao Ito, Amlan Kar, Oula Kalttopää, Deirdre Kerdraon, Erik Kristensen, Jaclyn McKeown, Tommi Mononen, Ellen Nein, Hanna Rogers, Tomas Roslin, Paula Schmitz, Jayme Sones, Maija Sujala, Amy Thompson, Evgeny V. Zakharov, Iuliia Zarubiieva, Akshita Gupta, Scott Lowe, Graham Taylor
Scientific Data, 2026
A paired image-and-DNA dataset of insects captured at both the trap and the individual level, for automated monitoring.
Paper
Self-Distillation of Hidden Layers for Self-Supervised Representation Learning
Scott Lowe, Anthony Fuller, Sageev Oore, Evan Shelhamer, Graham Taylor
arXiv preprint arXiv:2603.15553, 2026
Self-distilling intermediate layer representations to improve self-supervised visual learning.
arXiv
CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale
ZeMing Gong, Austin Wang, Xiaoliang Huo, Joakim Bruslund Haurum, Scott Lowe, Graham Taylor, Angel Chang
International Conference on Learning Representations (ICLR), 2025
Contrastive learning across images, DNA barcodes, and taxonomic labels for zero-shot insect classification.
BarcodeMamba: State Space Models for Biodiversity Analysis
Tiancheng Gao, Graham Taylor
Neural Information Processing Systems (NeurIPS) Workshop on Foundation Models for Science, 2024
State-space models applied to DNA barcode sequences for taxonomic classification at scale.
BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity
Zahra Gharaee, Scott Lowe, ZeMing Gong, Pablo Millan Arias, Nicholas Pellegrino, Austin Wang, Joakim Bruslund Haurum, Iuliia Zarubiieva, Lila Kari, Dirk Steinke, Graham Taylor, Paul Fieguth, Angel Chang
Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track, 2024
A multimodal dataset of over 5 million insect specimens with images, DNA barcodes, and taxonomic labels.
Selected publications →

Group

Photo of Emma Boehly
Emma Boehly
Research Associate
Photo of Iuliia Eyriay
Iuliia Eyriay
Postdoctoral Fellow & Research Manager
Photo of Michal Lisicki
Michal Lisicki
PhD Student
Photo of Mohamed Mostafa
Mohamed Mostafa
MASc Student
Photo of Nathan Grewal
Nathan Grewal
PhD Student
Photo of Scott Lowe
Scott Lowe
Postdoctoral Fellow
Photo of Tiancheng Gao
Tiancheng Gao
MASc Student
Photo of Vivian Phung
Vivian Phung
MSc Student
Alumni & former members →

Want to join the lab?

We're a remote-friendly ML research lab that publishes openly and ships datasets and tools researchers actually use. If you want to know what it's like to work here, read on.

How We Work