Princeton University PCTS Workshop

AI-Accelerated Quantum Materials: From Method Development to Novel Materials (AAQM)

Organizers: Andrei Bernevig and Leslie Schoop, Shuo Liu, Yi Jiang (Princeton University) JiabinYu, Benjamin Geisler, Richard Hennig, and Peter Hirschfeld (University of Florida)

Registration is open. https://forms.gle/KYXWRfP3c9nPpekbA

Description:  This workshop will bring together researchers working at the intersection of artificial intelligence, quantum materials,superconductivity, and experimental materials discovery. Its central goal is to assess how modern machine-learning methods can move beyond retrospective data mining and become practical tools for discovering, understanding, and ultimately realizing new superconducting materials. The program will cover emerging approaches to crystal-structure prediction, generative models for quantum materials, machine learning interatomic potentials, autonomous and closed-loop materials discovery, and physics-informed models that incorporate symmetry, bonding, quantum geometry, and electron–phonon coupling. A major emphasis will be placed on the full discovery pipeline: from theoretical design and high-throughput screening to synthesizability, experimental validation, and the interpretation of failed or ambiguous predictions.

By bringing together theorists, computational materials scientists, machine-learning researchers, chemists, and experimentalists, the workshop aims to identify the current bottlenecks in AI-driven superconductor discovery and to define a shared roadmap for the field. Particular attention will be given to the gap between predicted and realized materials, the need for high-quality shared datasets and benchmarks, and the role of physics constraints in making AI-generated materials scientifically meaningful.

Representative themes include: AI-guided crystal and compound discovery; inverse design of superconductors; quantum geometry and electron–phonon coupling; synthesizability and validation; autonomous laboratories and closed-loop feedback; foundation models for materials; and the creation of community datasets for superconductivity and quantum materials.

This workshop will include a poster session.  To apply to present a poster, please complete the relevant sections on the registration form no later than October 16.  We will contact you with more details after October 16. 

Registration is free, but required for in-person attendance. You must be a current faculty member, researcher, or graduate student at an accredited institution to register and attend.

Sponsors

  • PCTS
  • University of Florida

Related documents

Date & Time

November 09, 2026 | 8:00am – 5:00pm
Add to calendar 11/09/2026 08:00 11/09/2026 17:00 Princeton University PCTS Workshop use-title Topic: AI-Accelerated Quantum Materials: From Method Development to Novel Materials (AAQM) More: https://www.ias.edu/sns/events/princeton-university-pcts-workshop-26 ORGANIZERS: ANDREI BERNEVIG AND LESLIE SCHOOP, SHUO LIU, YI JIANG (PRINCETON UNIVERSITY) JIABINYU, BENJAMIN GEISLER, RICHARD HENNIG, AND PETER HIRSCHFELD (UNIVERSITY OF FLORIDA) REGISTRATION IS OPEN. HTTPS://FORMS.GLE/KYXWRFP3C9NPPEKBA DESCRIPTION:  This workshop will bring together researchers working at the intersection of artificial intelligence, quantum materials,superconductivity, and experimental materials discovery. Its central goal is to assess how modern machine-learning methods can move beyond retrospective data mining and become practical tools for discovering, understanding, and ultimately realizing new superconducting materials. The program will cover emerging approaches to crystal-structure prediction, generative models for quantum materials, machine learning interatomic potentials, autonomous and closed-loop materials discovery, and physics-informed models that incorporate symmetry, bonding, quantum geometry, and electron–phonon coupling. A major emphasis will be placed on the full discovery pipeline: from theoretical design and high-throughput screening to synthesizability, experimental validation, and the interpretation of failed or ambiguous predictions. By bringing together theorists, computational materials scientists, machine-learning researchers, chemists, and experimentalists, the workshop aims to identify the current bottlenecks in AI-driven superconductor discovery and to define a shared roadmap for the field. Particular attention will be given to the gap between predicted and realized materials, the need for high-quality shared datasets and benchmarks, and the role of physics constraints in making AI-generated materials scientifically meaningful. REPRESENTATIVE THEMES INCLUDE: AI-guided crystal and compound discovery; inverse design of… 407 Jadwin Hall, 4th Floor, PCTS Seminar Room a7a99c3d46944b65a08073518d638c23
November 10, 2026 | 8:00am – 5:00pm
Add to calendar 11/10/2026 08:00 11/10/2026 17:00 Princeton University PCTS Workshop use-title Topic: AI-Accelerated Quantum Materials: From Method Development to Novel Materials (AAQM) More: https://www.ias.edu/sns/events/princeton-university-pcts-workshop-26 ORGANIZERS: ANDREI BERNEVIG AND LESLIE SCHOOP, SHUO LIU, YI JIANG (PRINCETON UNIVERSITY) JIABINYU, BENJAMIN GEISLER, RICHARD HENNIG, AND PETER HIRSCHFELD (UNIVERSITY OF FLORIDA) REGISTRATION IS OPEN. HTTPS://FORMS.GLE/KYXWRFP3C9NPPEKBA DESCRIPTION:  This workshop will bring together researchers working at the intersection of artificial intelligence, quantum materials,superconductivity, and experimental materials discovery. Its central goal is to assess how modern machine-learning methods can move beyond retrospective data mining and become practical tools for discovering, understanding, and ultimately realizing new superconducting materials. The program will cover emerging approaches to crystal-structure prediction, generative models for quantum materials, machine learning interatomic potentials, autonomous and closed-loop materials discovery, and physics-informed models that incorporate symmetry, bonding, quantum geometry, and electron–phonon coupling. A major emphasis will be placed on the full discovery pipeline: from theoretical design and high-throughput screening to synthesizability, experimental validation, and the interpretation of failed or ambiguous predictions. By bringing together theorists, computational materials scientists, machine-learning researchers, chemists, and experimentalists, the workshop aims to identify the current bottlenecks in AI-driven superconductor discovery and to define a shared roadmap for the field. Particular attention will be given to the gap between predicted and realized materials, the need for high-quality shared datasets and benchmarks, and the role of physics constraints in making AI-generated materials scientifically meaningful. REPRESENTATIVE THEMES INCLUDE: AI-guided crystal and compound discovery; inverse design of… 407 Jadwin Hall, 4th Floor, PCTS Seminar Room a7a99c3d46944b65a08073518d638c23
November 11, 2026 | 8:00am – 5:00pm
Add to calendar 11/11/2026 08:00 11/11/2026 17:00 Princeton University PCTS Workshop use-title Topic: AI-Accelerated Quantum Materials: From Method Development to Novel Materials (AAQM) More: https://www.ias.edu/sns/events/princeton-university-pcts-workshop-26 ORGANIZERS: ANDREI BERNEVIG AND LESLIE SCHOOP, SHUO LIU, YI JIANG (PRINCETON UNIVERSITY) JIABINYU, BENJAMIN GEISLER, RICHARD HENNIG, AND PETER HIRSCHFELD (UNIVERSITY OF FLORIDA) REGISTRATION IS OPEN. HTTPS://FORMS.GLE/KYXWRFP3C9NPPEKBA DESCRIPTION:  This workshop will bring together researchers working at the intersection of artificial intelligence, quantum materials,superconductivity, and experimental materials discovery. Its central goal is to assess how modern machine-learning methods can move beyond retrospective data mining and become practical tools for discovering, understanding, and ultimately realizing new superconducting materials. The program will cover emerging approaches to crystal-structure prediction, generative models for quantum materials, machine learning interatomic potentials, autonomous and closed-loop materials discovery, and physics-informed models that incorporate symmetry, bonding, quantum geometry, and electron–phonon coupling. A major emphasis will be placed on the full discovery pipeline: from theoretical design and high-throughput screening to synthesizability, experimental validation, and the interpretation of failed or ambiguous predictions. By bringing together theorists, computational materials scientists, machine-learning researchers, chemists, and experimentalists, the workshop aims to identify the current bottlenecks in AI-driven superconductor discovery and to define a shared roadmap for the field. Particular attention will be given to the gap between predicted and realized materials, the need for high-quality shared datasets and benchmarks, and the role of physics constraints in making AI-generated materials scientifically meaningful. REPRESENTATIVE THEMES INCLUDE: AI-guided crystal and compound discovery; inverse design of… 407 Jadwin Hall, 4th Floor, PCTS Seminar Room a7a99c3d46944b65a08073518d638c23

Location

407 Jadwin Hall, 4th Floor, PCTS Seminar Room