发表机构
Khalifa University of Science and Technology; University of Wolverhampton（哈利法科学技术大学; 伍尔弗汉普顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出将喷注信息栅格化为四面板图像，用视觉-语言模型统一处理多任务喷注分析，实验表明参数高效适配后性能优异，支持未来对撞机数据。
AI 中文摘要
高能物理（HEP）对撞机上记录的海量数据使得物理对象的精确识别成为解析事件拓扑的瓶颈，而机器学习已成为喷注标记的标准工具。在本工作中，我们考察了视觉-语言模型（VLMs）能否为基于单一物理信息图像的结构化喷注分析提供通用接口。每个JetClass喷注被转换为224x224的RGB图像，包含四个面板，分别编码所有成分的p_T流；带电强子、中性强子和电磁成分；p_T加权的碰撞参数显著性与位移径迹多重性；以及带符号径迹p_T密度与局部p_T^k加权的喷注电荷不对称性。我们采用低秩适配（LoRA）对四个开源VLM进行适配，用于QCD、Higgs、W/Z和top喷注的类别分类、六场属性预测以及通过替换面板定位实现的跨面板一致性检验，并在24000个平衡的JetClass测试喷注上评估。消融实验表明，重味标记的碰撞参数寿命特征是主导因素，而喷注电荷可区分近乎质量简并的强子W和Z。零样本召回率接近随机水平（3.33%-10.57%），一旦适配，任务1的宏召回率随训练规模单调增长，Gemma4-E4B达到75.05%（F_1为74.87%），任务2场平均为93.31%，二分类/定位召回率分别为99.88%/99.75%。将预算重新分配至W/Z喷注可使Zqq召回率提高最多9.83个百分点，同时宏召回率几乎不变。向更广泛拓扑的JetClass-II和真实数据Aspen Open Jets（探测模拟到数据差距）的迁移得以保留：使用3000个目标喷注时，任务1召回率在JetClass-II上超过70%，且任务2和任务3的每个指标均超过92%。因此，将能量流、种类、位移和喷注电荷栅格化，结合参数高效适配，支持通过单一指令条件接口对未来对撞机数据进行喷注分析。
英文摘要
The enormous recorded data at high-energy physics (HEP) colliders make the accurate identification of physics objects a bottleneck in disentangling event topologies, where machine learning has become a standard tool for jet tagging. In this work, we examine whether Vision-Language Models (VLMs) can provide a common interface for structured jet analysis from a single physics-informed image. Each JetClass jet becomes a 224x224 RGB image with four panels encoding p_T flow of all constituents; charged-hadron, neutral-hadron, and electromagnetic composition; p_T-weighted impact-parameter significances with displaced-track multiplicity; and signed-track p_T densities with local p_T^k-weighted jet-charge asymmetry. Four open VLMs are adapted with low-rank adaptation (LoRA) for class classification across QCD, Higgs, W/Z, and top jets, six-field attribute prediction, and cross-panel consistency with replaced-panel localization, evaluated on 24000 balanced JetClass test jets. Ablations identify the impact-parameter lifetime signature of heavy-flavor tagging as dominant, with jet charge separating the nearly mass-degenerate hadronic W and Z. Zero-shot recall stays near chance (3.33%-10.57%), once adapted, Task 1 Macro recall grows monotonically with training size, and Gemma4-E4B reaches 75.05% (74.87% F_1), 93.31% Task 2 field-mean, and 99.88%/99.75% binary/localization recall. Reallocating budget toward W/Z jets raises Zqq recall by up to 9.83 points at near-constant Macro recall. Transfer to broader-topology JetClass-II and real-data Aspen Open Jets (probing the simulation-to-data gap) is retained: with 3000 target jets, Task 1 recall exceeds 70% on JetClass-II and every Task 2/3 metric exceeds 92%. Thus rasterizing energy flow, species, displacement, and jet charge, with parameter-efficient adaptation, supports jet analysis through one instruction-conditioned interface for future collider data.
Comments30 pages, 9 figures, 20 tables. Comments are welcome
