Nolan Koblischke

Nolan Koblischke

AI + astrophysics

nolan.koblischke@mail.utoronto.ca

Now (as of Nov. 2026): Working on language models for discovery in astronomy.

PhD: Astrophysics @ Toronto - Advisor: Jo Bovy - Expected 2028

Latest News: Organizing ML4PS 2026. ChatGPT Futures award and Universe Today interview.

Research

GalaxyWiki: Extracting Published Discussions of 13,616 Galaxies with Language Models

Our attempt at extracting everything ever said about every galaxy. GalaxyWiki brings together more than 44,000 discussions of 13,616 galaxies, with excerpts and links to the original papers.

Identifying Scientifically Interesting Galaxies with Vision-Language Models

A two-by-two montage of three DESI Legacy Imaging Surveys DR10 galaxies and a black-and-white Hubble image of the strong gravitational lens SDSS J1205+4910

We ranked Hubble images by scientific interest with vision-language models. Gemini recovered 98.2% of 167 reference anomalies in the 2,095 highest-scoring images.

AION-Search: Semantic Search for 100M+ Galaxy Images Using AI-Generated Captions

AION-Search

A text-based search engine for galaxy images trained on AI-generated captions. Enables flexible semantic search for rare phenomena without manual labeling.

Gravity-Bench-v1: A Benchmark on Gravitational Physics Discovery for Agents

GravityBench

A benchmark that challenges AI agents on gravitational physics discovery tasks, evaluating scientific reasoning and observational planning capabilities within controlled, physics-based environments.

AstroCoder: AI-Powered Discovery and Usage of Astronomy Software

AstroCoder

Transforming how astronomers discover code: AI-powered search across 2,270 astronomy tools. From finding the right package to generating working examples in seconds.

SpectraFM: Tuning into Stellar Foundation Models

SpectraFM
📄 arXiv:2411.04750

A Transformer-based model capable of processing stellar spectra across any wavelength range.

Calibrating and standardizing the Tip of the Red Giant Branch in the Small Magellanic Cloud using small-amplitude red giants

SMC
📄 arXiv:2406.19375

Discovered that pulsation impacts the TRGB in the SMC as in the LMC, with older, longer period pulsators leading to a highly accurate TRGB tip measurement.

Small-amplitude Red Giants Elucidate the Nature of the Tip of the Red Giant Branch as a Standard Candle

LMC
📄 arXiv:2303.04790

Discovered that red giant pulsation adds a new dimension of the TRGB method, leading to an enhanced method for measuring the Universe's expansion rate.

Featured in: EPFL News, Space.com, Universe Today, Phys.org, Tech Explorist, MyScience

ChatGaia: Natural Language Interface to the Gaia Space Telescope

ChatGaia

Making 2 billion stars queryable through conversation. Reached 70,000+ viewers and used thousands of times.

Talks

Semantic search for 100M+ galaxy images using AI-generated captions
Talk, Harvard-Smithsonian CfA, 2026

Teaching ChatGPT to Do Real Science
Fraser Cain / Universe Today Podcast

Panelist, "AI & Physics: Learning from Each Other" (Not recorded)
Vector Institute Foundation Models for Science, Toronto, 2025

UniverseTBD & AstroCoder (10:00-)
Theory + AI Symposium, Perimeter Institute

Gravity Bench: A Benchmark on Gravitational Physics Discovery for Agents
ESO Natural Language Processing in Astronomy

Gravity Bench: A Benchmark on Gravitational Physics Discovery for Agents
NLP for Space Science Workshop, ESA/ESAC, Madrid

SpectraFM: Tuning into Stellar Foundation Models
AstroAI Workshop, Harvard-Smithsonian CfA

ChatGaia: Talk to the Gaia Archive in Natural Language
Debating the Potential of Machine Learning in Astronomical Surveys, Flatiron