arXiv:2605.26821v1 Announce Type: cross Abstract: The Lund plane offers a physics-motivated, hierarchical representation of QCD radiation within jets, while transformer-based taggers have reached state-of-the-art performance by learning directly from raw particle constituents and their pairwise relations. We investigate whether transformers implicitly capture hierarchical QCD structure from constituent-level inputs, or whether explicit physics representations remain complementary. To test this, we introduce PLuM, a multimodal architecture that projects particle constituents and Lund plane spli
The proliferation of advanced AI techniques, particularly transformer models, is prompting research into their application and integration with established physics-based representations to enhance complex data analysis.
This research contributes to the development of more sophisticated and interpretable AI for scientific discovery, potentially accelerating breakthroughs in fields like high-energy physics.
The explicit incorporation of physics-motivated hierarchical structures (Lund plane) into transformer-based AI for jet tagging suggests a hybrid approach to AI model design for scientific tasks.
- · High-energy physics researchers
- · AI model developers
- · Scientific computing platforms
- · Traditional, purely black-box AI approaches in science
Improved performance and interpretability of AI models for particle physics analysis.
Faster and more reliable identification of new phenomena in collider experiments.
The development of hybrid AI architectures that blend deep learning with domain-specific knowledge becoming a standard practice in scientific AI.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG