paper-with-me

홈 › Papers

OmniJet-$α$: The first cross-task foundation model for particle physics

2024-03-08 · Joschka Birk, Anna Hallin, Gregor Kasieczka

Foundation models are multi-dataset and multi-task machine learning methods that once pre-trained can be fine-tuned for a large variety of downstream applications. The successful development of such general-purpose models for physics data would be a major breakthrough as they could improve the achievable physics performance while at the same time drastically reduce the required amount of training time and data. We report significant progress on this challenge on several fronts. First, a comprehensive set of evaluation methods is introduced to judge the quality of an encoding from physics data into a representation suitable for the autoregressive generation of particle jets with transformer architectures (the common backbone of foundation models). These measures motivate the choice of a higher-fidelity tokenization compared to previous works. Finally, we demonstrate transfer learning between an unsupervised problem (jet generation) and a classic supervised task (jet tagging) with our new OmniJet-$\alpha$ model. This is the first successful transfer between two different and actively studied classes of tasks and constitutes a major step in the building of foundation models for particle physics.

📄 PDF Abstract BibTeX arXiv:2403.05618

Code (1)

uhh-pd-ml/omnijet_alpha 공식 구현 pytorch

Tasks

Jet TaggingTransfer Learning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Enhancing next token prediction based pre-training for jet foundation models

2025-12-03 · Joschka Birk, Anna Hallin, Gregor Kasieczka, Nikol Madzharova 외 arxiv

Next token prediction is an attractive pre-training task for jet foundation models, in that it is simulation free and enables excellent generative capabilities that can transfer across datasets. Here we study multiple im…

Aspen Open Jets: Unlocking LHC Data for Foundation Models in Particle Physics

2024-12-13 · Oz Amram, Luca Anzalone, Joschka Birk, Darius A. Faroughy 외

Foundation models are deep learning models pre-trained on large amounts of data which are capable of generalizing to multiple datasets and/or downstream tasks. This work demonstrates how data collected by the CMS experim…

OmniJet-$α_C$: Learning point cloud calorimeter simulations using generative transformers

2025-01-09 · Joschka Birk, Frank Gaede, Anna Hallin, Gregor Kasieczka 외

We show the first use of generative transformers for generating calorimeter showers as point clouds in a high-granularity calorimeter. Using the tokenizer and generative part of the OmniJet-${\alpha}$ model, we represent…

Cross-Domain Transfer with Particle Physics Foundation Models: From Jets to Neutrino Interactions

2026-04-14 · Gregor Krzmanc, Vinicius Mikuni, Benjamin Nachman, Callum Wilkinson arxiv

Future AI-based studies in particle physics will likely start from a foundation model to accelerate training and enhance sensitivity. As a step towards a general-purpose foundation model for particle physics, we investig…

Binary Classification

A Language Model for Particle Tracking

2024-02-14 · Andris Huang, Yash Melkani, Paolo Calafiura, Alina Lazar 외

Particle tracking is crucial for almost all physics analysis programs at the Large Hadron Collider. Deep learning models are pervasively used in particle tracking related tasks. However, the current practice is to design…

Deep LearningLanguage ModelingLanguage Modellingmodel