BEGIN:VCALENDAR VERSION:2.0 PRODID:-//CERN//INDICO//EN BEGIN:VEVENT SUMMARY:Scattering Amplitudes: A New Playground for Machine Learning DTSTART;VALUE=DATE-TIME:20250425T030000Z DTEND;VALUE=DATE-TIME:20250425T040000Z DTSTAMP;VALUE=DATE-TIME:20250722T050400Z UID:indico-event-25748@indico.ihep.ac.cn DESCRIPTION:Speakers: Tianji 恬吉 Cai蔡 (SLAC National Accelerator Labo ratory)\nAI for fundamental physics is now a burgeoning field\, with nume rous efforts pushing the boundaries of experimental and theoretical physic s\, as well as machine learning research itself. In this talk\, I will int roduce a recent innovative application of Natural Language Processing to t he state-of-the-art precision calculations in high energy particle physic s. Specifically\, we use Transformers to predict symbolic mathematical ex pressions that represent scattering amplitudes in planar N=4 Super Yang-Mi lls theory—a quantum field theory closely related to the real-world QCD at the Large Hadron Collider. Our first results have demonstrated great pr omises of Transformers for amplitude calculations\, while its major chal lenges are being addressed by ongoing work. This study opens the door for an exciting new scientific paradigm where discoveries and human insights a re inspired and aided by an AI agent.\n\nBio: Tianji Cai (蔡恬吉) is a postdoctoral research associate in the Fundamental Physics Directorate at the SLAC National Accelerator Laboratory\, and a research affiliate at the Lawrence Berkeley National Laboratory. She obtained her Ph.D. degree in 2 023 at University of California\, Santa Barbara\, and holds two bachelor's degrees from Duke University and Shanghai Jiao Tong University. Her resea rch interest lies at the intersection of High Energy Theory (HEP) and Arti ficial Intelligence (AI)\, with a focus on developing novel machine learni ng frameworks for collider phenomenology and scattering amplitudes. She’ s also interested in using HEP to aid theoretical understanding of AI syst ems.\n\n*请线下参加报告的外单位老师、同学注册时填写 个人信息（中文姓名、身份证号码及手机号码），用于 预约进入物理学院。\nhttps://indico.ihep.ac.cn/event/25748/ LOCATION:B105 (CHEP) URL:https://indico.ihep.ac.cn/event/25748/ END:VEVENT END:VCALENDAR