构建可处理离散与连续数据的核物理基础模型，提升探测器信号生成精度。
Towards Foundation Models for Experimental Readout Systems Combining Discrete and Continuous Data
- 分离离散与连续变量词汇表，用跨注意力融合多模态输入
- 实现高分辨率光子像素与时间序列快速生成，闭合测试验证有效
- 支持条件生成与微调，适用于粒子识别与降噪任务
我们提出一种面向核物理的（原型）基础模型，可处理未来电子离子对撞机中成像切伦科夫探测器的低层输入信号。基于经典的下一步预测范式，旨在解决现有分词方案导致的分辨率损失及条件生成能力不足等问题。提出四项关键创新：(i) 分离离散与连续变量的词汇表，通过因果多头交叉注意力（CMHCA）联合建模；(ii) 通过预追加上下文嵌入实现连续运动学条件控制；(iii) 实现无联合词表膨胀的高分辨率连续变量分词，具有可扩展性与简洁性；(iv) 借助专家混合机制实现类别条件生成。模型在高性能DIRC系统中通过闭合测试验证了像素与时间序列生成的高速与高保真性。此外，模型还展现出对π/ K 粒子识别和噪声过滤等重建任务的泛化能力，可通过特定目标进行微调以优化性能。
原文摘要 · Abstract (English)
We present a (proto) Foundation Model for Nuclear Physics, capable of operating on low-level detector inputs from Imaging Cherenkov Detectors at the future Electron Ion Collider. Building upon established next-token prediction approaches, we aim to address potential challenges such as resolution loss from existing tokenization schemes and limited support for conditional generation. We propose four key innovations: (i) separate vocabularies for discrete and continuous variates, combined via Causal Multi-Head Cross-Attention (CMHCA), (ii) continuous kinematic conditioning through prepended context embeddings, (iii) scalable and simple, high-resolution continuous variate tokenization without joint vocabulary inflation, and (iv) class conditional generation through a Mixture of Experts. Our model enables fast, high-fidelity generation of pixel and time sequences for Cherenkov photons, validated through closure tests in the High Performance DIRC. We also show our model generalizes to reconstruction tasks such as pion/kaon identification, and noise filtering, in which we show its ability to leverage fine-tuning under specific objectives.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。