Probing the frontiers of nuclear physics with AI at the EIC (II)
In recent years, significant breakthroughs in artificial intelligence (AI) and machine learning (ML) have been achieved including generative models based on diffusion and Large Language Models (LLMs) for text and code generation. These tools are increasingly applied and developed in the context of research on fundamental physics. Given the rapid developments in this area of research, we will host the second iteration of the 2023 CFNS workshop on “Probing the frontiers of nuclear physics with AI at the Electron-Ion Collider (EIC).” The EIC will be the main US-based nuclear collider experiment, where QCD dynamics and the structure of hadrons will be studied in great detail. To realize the scientific goals, various challenges in theory, data science, and experiments remain where AI applications can advance scientific discoveries. Our goal is to bring together AI/ML experts and researchers focusing on hadron structure, lattice QCD, nuclear many-body physics, experiment design, and data analysis at collider experiments to discuss recent progress and explore common interests and applications. While the workshop will be focused primarily on aspects of nuclear physics at the future EIC, connections to adjacent fields such as heavy-ion and high-energy physics at RHIC and the LHC, computer science, and quantum computing will be discussed as well to provide a comprehensive overview and encourage interdisciplinary collaborations.
Specific topics:
- Inverse problems and high dimensional unfolding
- Foundation models
- AI lattice field theory calculations
- Tensor networks and neural network quantum states
- Generative modeling of collider events, jets, and detectors
- Large Language Models (LLMs) for fundamental physics
- Experimental challenges in nuclear tomography at the EIC
Organizing committee:
Miguel Arratia (UC Riverside)
Dmitri Kharzeev (Stony Brook U./BNL)
Felix Ringer (Stony Brook U.)
Nobuo Sato (JLab)
Phiala Shanahan (MIT)
The workshop will be held in person but a remote listener option via Zoom will be available for registered participants. This event is part of the CFNS workshop/ad-hoc meeting series. See the CFNS conferences page for other events.