Spring 2026 IHEP ML Workshop

Session

Parallel-2

15 Apr 2026, 09:00

Conveners

Parallel-2: Fast ML & 生成式模型

• 芹 袁 (高能所)
• 世聪 胡 (高能所)
• Tong Liu (IHEP)

Parallel-2: Embedding & Multi-Modal

• 浩 王 (中国科学院高能物理研究所东莞分部（中国散裂中子源）)
• Xiaopeng Zhang (IHEP)
• Wang Ji (IHEP)

Description

会议室多学科228
https://meeting.tencent.com/dm/HDS2NKxYI0Gj

腾讯会议：511-900-966

Contribution list Timetable

32. Fast simulation using MoE+cGAN for BESIII Calorimeter

Tong Liu (IHEP)

15/04/2026, 09:00

33. Fast simulation with diffusion model for BESIII Calorimeter

Mr Qiaojia Ge

15/04/2026, 09:20

9. STCF Electromagnetic Calorimeter Fast Simulation based on GAN

潇 杨

15/04/2026, 09:40

Super Tau Charm Facility(STCF), as a new-generation high-luminosity collider experiment, places higher demands on the generation of large-scale Monte Carlo samples.MC simulation, especially for electromagnetic calorimeter(ECAL), requires substantial computational resources. Traditional Geant4 approach simulates the secondary particles and interactions of electromagnetic showers in ECAL. But...

34. Fast ML in BESIII Trigger

瀚林 张 (高能所)

15/04/2026, 10:00

8. 面向机器学习径迹重建的漂移室数据集

Liyan Qian

15/04/2026, 10:40

近几年随着人工智能技术的发展，机器学习（Machine Learning，ML），尤其是图神经网络（Graph Neural Networks，GNNs），为径迹重建提供了全新解决方案并取得显著结果。然而，当前相关研究仍面临关键瓶颈：公开数据集与评估指标尚不统一，现有数据集多面向强子对撞机的高堆积、高多重数环境设计，与$\tau$-粲物理实验所对应的低本底、低多重数、高精度测量需求存在显著差异，导致面向$\tau$-粲物理实验的专用数据集与评估指标长期缺失，严重限制了相关ML方法的公平对比与快速迭代。

针对上述难题，本工作构建了一套完整的数据集产生与径迹重建性能分析工作体系。首先通过单粒子与多粒子产生子完成蒙特卡洛（Monte Carlo, MC）模拟数据生成，并设计预处理流程构建机器学习径迹重建数据集；随后将机器学习寻迹结果通过外联式导入或内联式推理两种方式集成到 BOSS...

5. Anomaly Detection for Defect Identification in CMS HGCAL Assembly at IHEP

suyun huang

15/04/2026, 11:00

This talk presents a machine learning–based approach for automated defect detection in CMS HGCAL assembly. A hybrid framework combining supervised object detection (YOLO) and unsupervised anomaly detection (PatchCore) is developed to identify defects such as glue leakage and abnormal wire bonding. The method achieves strong performance in controlled conditions and demonstrates the advantage of...

31. Cross-dataset anomaly detection

宇遥 徐

15/04/2026, 11:20

35. Multi-Modal overview

Wang Ji (IHEP) , Xiaopeng Zhang (IHEP) , 浩 王 (中国科学院高能物理研究所东莞分部（中国散裂中子源）)

15/04/2026, 11:40

36. 多模态数据分析智能体：源源

庆梦 李 (高能所)

15/04/2026, 12:00