AI diffusion models applied to particle physics for parameter discovery

Researchers have developed a novel approach using diffusion models, a type of generative AI, to search for parameters within flavor models that align with experimental constraints. This method was applied to the $S_4^\prime$ modular flavor model, where a neural network was trained to predict quark masses, the CKM matrix, and the Jarlskog invariant based on free parameters. The study identified new phenomenologically interesting parameter regions and confirmed spontaneous CP violation in the $S_4^\prime$ model, demonstrating the diffusion model's capability for inverse problem solving in physics. AI

IMPACT This research demonstrates a new AI-driven method for solving inverse problems in theoretical physics, potentially accelerating discovery in particle physics.

RANK_REASON The cluster contains a research paper detailing a novel application of AI to a specific scientific problem. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• CKM matrix
• diffusion models
• generative AI
• High Energy Physics - Phenomenology
• Hugging Face
• Jarlskog invariant
• quark masses
• $S_4^\prime$ modular flavor model
• Satsuki Nishimura

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →