arXiv · 2606.23791
One Generator, Any Process: LLM-Conditioning for the LHC
Abstract
Neural network training for LHC event generation should, ideally, benefit from common high-level patterns in different processes. We propose novel conditioning schemes for continuous parameters, process labels, and Feynman diagrams. We employ pre-trained LLMs as multi-modal foundation models to provide descriptive embeddings for an autoregressive transformer. With such high-level physics-inductive bias the generative networks converge faster, provide better result, and generalize to unseen processes.
Explore related subjects
Keep this discovery
Henning Bahl, Tilman Plehn, Daniel Schiller, Thanush Sivagnanalingam. 2026-06-22. One Generator, Any Process: LLM-Conditioning for the LHC. https://arxiv.org/abs/2606.23791
Cite the original work for its findings. Save a collection to share your selection of sources.