NASA Cosmic Origins Program

AI/ML Science & Technology
Interest Group

Building AI literacy for astronomical research through stackable, bite-sized modular training designed for the astronomy community.

Our Mission

About the STIG

The NASA Cosmic Origins Program AI/ML Science and Technology Interest Group (AI/ML STIG) addresses the critical need to upskill the astronomy community with AI literacy. We provide structured, domain-specific AI education through stackable, bite-sized modular training designed for astronomical research contexts.

Established under the Cosmic Origins Program Analysis Group (COPAG), the STIG brings together researchers and educators to build a comprehensive AI education framework tailored for the astronomy community.

23
Week Series
8
Modules
Open
To Everyone
Lecture Series

Program Schedule

A 23-week open-source lecture series. Click any row with aVideo & Materialsbadge to expand recordings, notebooks, and slides.

Duration
23 weeks (Nov 2025 - May 2026)
Format
Weekly 1-hour sessions
Time
Mondays at 4:00 PM ET
Delivery
Remote only
WeekDateTopicSpeaker
1Nov 3
OverviewVideo & Materials
Jesse Thaler, MIT
Module 1: Large Language Models as Autonomous Agents
2Nov 10
LLM API BasicsVideo & Materials
Yuan-Sen Ting, OSU
3Nov 17
RAG & Function ToolsVideo & Materials
Yuan-Sen Ting, OSU
4Nov 24
LLM as AgentVideo & Materials
Francisco Villaescusa-Navarro, Flatiron
5Dec 8
Model Context Protocol (MCP)Video & Materials
Yuan-Sen Ting, OSU
Module 2: Deep Learning Frameworks
6Dec 15
PyTorch and AutodifferentiationVideo & Materials
Phill Cargile, Harvard-Smithsonian
7Dec 22
JAXVideo & Materials
Phill Cargile, Harvard-Smithsonian
Module 3: Neural Network Basics
8Jan 12
Inductive BiasesVideo & Materials
John Wu, STScI
9Jan 26
Convolutional Neural Networks (CNNs)Video & Materials
John Wu, STScI
10Feb 2
Graph Neural Networks (GNNs)Video & Materials
Tri Nguyen, Northwestern
11Feb 9
TransformersVideo & Materials
Helen Qu, Flatiron
12Feb 23
Recurrent Neural Networks (RNNs)Video & Materials
Daniel Muthukrishna, Harvard/MIT
Module 4: Physics-Inspired Networks
13Mar 2
Equivariant Neural Networks (Theory)
Anna Scaife, U. of Manchester
14Mar 9
Equivariant Neural Networks (Application)
Anna Scaife, U. of Manchester
Module 5: Generative Models
15Mar 16
Normalizing Flows
Gregory Green, Westlake
16Mar 23
Diffusion Models
Duo Xu, U. of Toronto
17Mar 30
Flow Matching
Tomasz Rozanski, ANU
18Apr 6
Simulation-Based Inference
Tomasz Rozanski, ANU
Module 6: Ethics and Philosophy of Science
19Apr 13
Peer Review with AI: Promise and Pitfalls
Licia Verde, U. of Barcelona/JCAP
20Apr 27
The Meaning of Understanding in AI-Laden Science
Siyu Yao, STJU
Module 7: NSF Funding Opportunity
21Apr 20
NSF Funding Opportunity
Andrea Berlind, NSF
Module 8: Reinforcement Learning
22May 4
Reinforcement Learning Fundamentals
Carol Cuesta-Lazaro, IAS/Flatiron
23May 11
Reinforcement Learning Applications
Carol Cuesta-Lazaro, IAS/Flatiron
Team

Leadership Council

Yuan-Sen Ting(Chair)
The Ohio State University
Andrew Saydjari
Princeton University
Alex Gagliano
MIT
Carol Cuesta-Lazaro
Institute for Advanced Study at Princeton/Flatiron Institute
Digvijay Wadekar
University of Texas at Austin
Georgios Valogiannis
University of Chicago
Siddharth Mishra-Sharma
Boston University

For inquiries, please contact: ting.74@osu.edu

Join Us

How to Participate

Membership

The AI/ML STIG is open to the national and international community without regard to institutional affiliation, education, or career status. We welcome astronomers, astrophysicists, data scientists, and anyone interested in AI applications in astronomy.

Join Mailing List

Recordings

All lecture recordings are hosted on the NASA Cosmic Origins Program subpage, making them accessible to the broader community for asynchronous learning. Past lectures include YouTube recordings embedded directly in each lecture card above.

NASA Official Page