发表机构
Stanford University; SLAC National Accelerator Laboratory（斯坦福大学; SLAC国家加速器实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究首次将工业基础模型TimesFM微调并蒸馏用于粒子物理DAQ，通过FPGA协同设计实现实时运行，性能达到或超过现有方案，且流程可推广至其他一维波形任务。
AI 中文摘要
未来粒子物理实验的数据采集（DAQ）系统有望受益于人工智能/机器学习发展的两个极端：大规模基础模型可以增强特征提取算法的性能，而探测器上的小规模部署可以实现实时智能数据处理。本研究首次针对粒子物理DAQ对工业基础模型进行微调。从谷歌研究TimesFM（时间序列基础模型）的主干网络出发，我们展示了在漂移室径迹探测器和双读出量能器的实时回归任务上的微调。此外，微调后的TimesFM模型被蒸馏为学生模型，并与FPGA实现进行协同设计，使这些模型能够在未来对撞机上实时运行。微调后的蒸馏模型在每个任务上的性能达到或超过先前发表的AI/ML解决方案。此外，从TimesFM进行蒸馏和模型压缩的流程具有通用性，可以轻松适应跨领域的各种一维波形任务。
英文摘要
Data acquisition (DAQ) systems at future particle physics experiments stand to benefit from the extremes of AI/ML development: large-scale foundation models can enhance the performance of feature extraction algorithms, and small-scale on-detector deployments can enable real-time intelligent data handling. This work provides the first fine-tuning of an industrial foundation model for particle physics DAQ. Starting from the backbone of Google Research's TimesFM (Time Series Foundation Model), we demonstrate fine-tuning on real-time regression tasks for drift chamber trackers and dual-readout calorimeters. Furthermore, the fine-tuned TimesFM model is distilled into a student and co-designed with FPGA implementation to enable these models to run in real-time at future colliders. The fine-tuned distillations meet or exceed the performance of previously published AI/ML solutions for each task. Further, the pipeline of distillation and model compression from TimesFM is generic and can be easily adapted to a variety of 1D waveform tasks across domains.
Comments7 pages, 1 figure, 1 table
