arXiv：cs.LG（机器学习，全量分类）· Dan Godi, Dmitrii Kobylianskii, Eilam Gross·· 13 小时前AI 评分34
用残差量化 token 扩展对撞机事件生成
Scaling Collider Event Generation with Residual-Quantized Tokens
AI 导读
研究提出一种基于残差量化全事件数据的粒子级生成模型，可对探测器稳定粒子进行条件生成，并系统考察了其在不同数据集与模型规模下的扩展行为。研究还刻画了重复数据暴露的影响，并证明 token 级损失能系统性预测下游物理保真度，为可扩展的对撞机全事件生成提供了实证框架。
正文
Abstract:Full detector simulation and reconstruction of collider events are projected to become major bottlenecks at the High-Luminosity Large Hadron Collider, motivating the development of fast, ML-based surrogates. At the same time, LLMs have driven fast progress in generative discrete modeling: autoregressive transformers trained on tokenized data now represent the state of the art across a range of generative tasks. We extend the discrete modeling paradigm by introducing a particle-level generative model trained on residual-quantized full-event data. We demonstrate the ability of this model family to perform conditional generation from detector-stable particles; we study its scaling behavior across a range of dataset and model sizes, characterize the effects of repeated data exposure and demonstrate that token-level loss systematically predicts downstream physical fidelity. These results provide an empirical framework for scalable collider full-event generation based on residual-quantized representations.
| Comments: | 10 pages + 11 pages of appendices, 12 figures, 10 tables |
| Subjects: | High Energy Physics - Experiment (hep-ex); Machine Learning (cs.LG); High Energy Physics - Phenomenology (hep-ph); Data Analysis, Statistics and Probability (physics.data-an) |
| Cite as: | arXiv:2610.00569 [hep-ex] |
| (or arXiv:2610.00569v1 [hep-ex] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00569 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dmitrii Kobylianskii [view email]
[v1]
Wed, 30 Sep 2026 18:43:13 UTC (1,401 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org