Description

One of the most important physical quantities in particle physics is the cross section, or a probability that a particular process takes place in the interaction of elementary particles. Its measure provides a testable link between theory and experiment. It is obtained theoretically mainly by calculating the squared amplitude. This project will explore language model joint embedding predictive architectures for calculation of squared amplitudes.

Duration

Total project length: 175/350 hours.

Task ideas and expected results

• Develop symbolic models to predict squared amplitudes based on reduced size versions of LLM-JEPA model architectures.
• Quantify the performance of LM-JEPA techniques.
• Document results formally or informally to support ongoing research.

Requirements

Significant experience with developing models in Python (preferably using pytorch). Experience with Joint Embedding Predictive Architectures and/or LLM development is preferred.

Difficulty Level

Advanced

Test

Please use this link to access the test for this project.

Mentors

• Eric Reinhardt (University of Alabama)
• Dinesh Ramakrishnan (University of Alabama)
• Sergei Gleyzer (University of Alabama)
• Nobuchika Okada (University of Alabama)
• Ritesh Bhalerao

Please DO NOT contact mentors directly by email. Questions should instead be directed to ml4-sci@cern.ch which is forwarded to mentors. To submit your proposal, CV, and test task solutions, please use this Google form.

Links

• Paper 1
• Paper 2

Corresponding Project

• SYMBA

Participating Organizations

• Alabama

---