Graduate Program Events |
Events on Friday, September 18th, 2026
- Preliminary Exam
- Intersecting AI and high energy theoretical physics
- Time: 9:00 am - 11:00 am
- Place: 5280 Chamberlin
- Speaker: Haotian Cao, Physics PhD Graduate Student
- Abstract: Artificial intelligence (AI) is increasingly advancing research in theoretical physics and pure mathematics. In this talk, I'll present two uses of AI in the context of conformal field theory and scattering amplitudes.
We first discuss an inverse problem emerging in two-dimensional conformal field theory (CFT): reconstructing tensor products of CFTs from their low-lying spectra. We specifically focus on rational conformal field theories (RCFTs) such as Wess-Zumino-Witten models characterized by affine Kac-Moody algebras. The discrete and structured nature of this problem for RCFTs motivates a sequence-to-sequence Transformer architecture that maps spectral information to the constituent affine algebras and central charges. We further demonstrate the model's ability to generalize to theories with larger central charges and to theories with unseen affine algebras during training.
We then turn to the amplitude bootstrap for N=4 super Yang-Mills theory (SYM) in the planar limit. We use agentic AI workflow to prove a mathematical conjecture related to the construction of a good basis in this program. Rather than relying solely on informal mathematical proofs, we use a systematic and iterative agentic AI workflow that translates the conjecture into formal mathematical statements, identifies the required intermediate lemmas, and constructs and verifies their proofs. - Host: Kyle Cranmer