Login

AI@LHC 2026: what's next?

25–29 May 2026
Peking University
Asia/Shanghai timezone

Contribution List

37 out of 37 displayed
Export to PDF
  1. 37. Morning Session 1 [Chaired by Qiang Li]
    25/05/2026, 08:59
  2. 2. Welcome
    Qinghong Cao (Peking University)
    25/05/2026, 09:00
  3. 27. Group Photo [outside open area]
    25/05/2026, 09:20
  4. 3. AI at the LHC
    Maurizio Pierini (CERN)
    25/05/2026, 09:30
  5. 4. AI for event simulation
    Francesco Vaselli (Scuola Normale Superiore & INFN Pisa (IT))
    25/05/2026, 10:10
  6. 29. Morning Session 2 [Chaired by Maurizio Pieini]
    25/05/2026, 11:19
  7. 5. AI for event reconstruction
    Farouk Mokhtar (Univ. of California San Diego (US))
    25/05/2026, 11:20
  8. 23. Towards a Physical Theory of Agents
    Huaxing Zhu (ITP, PKU)
    25/05/2026, 11:55
  9. 30. Afternoon Session [Chaired by Congqiao Li]
    25/05/2026, 13:59
  10. 6. Lecture + Tutorial 1: Machine Learning From Simple to Scale
    Huilin Qu (Tsung-Dao Lee Institute, Shanghai Jiao Tong University (CN))
    25/05/2026, 14:00
  11. 7. Octree-based 3D Neural Representation and Learning
    Prof. Peng-Shuai Wang (Wangxuan Institute of Computer Technology, Peking University)
    25/05/2026, 16:00

    Keynote talk
    https://wang-ps.github.io/

    Go to contribution page
  12. 32. Morning Session 1 [Chaired by Huilin Qu]
    26/05/2026, 08:59
  13. 8. Simulation-based inference for collider physics
    Jingjing Pan (KIT - Karlsruhe Institute of Technology (DE))
    26/05/2026, 09:00
  14. 10. Foundation Models for HEP
    Yulei Zhang (University of Washington (US))
    26/05/2026, 09:35
  15. 31. Morning Session 2 [Chaired by Congqiao Li]
    26/05/2026, 10:40
  16. 9. Simulation-based inference for precision neutrino physics [Remote]
    Dr Arsenii Gavrikov
    26/05/2026, 10:41
  17. 18. SAM 3D: 3Dfy Anything in Images [Remote]
    Weiyao Wang (Thinking Machines Lab)
    26/05/2026, 11:15

    Keynote talk
    https://sites.google.com/view/weiyaowang/home

    Go to contribution page
  18. 33. Afternoon Session [Chaired by Bingxuan Liu]
    26/05/2026, 13:59
  19. 11. Tutorial 2: Introduction to Fast Machine Learning
    Christopher Edward Brown (CERN), Maciej Mikolaj Glowacki (CERN)
    26/05/2026, 14:00

    Designing network that are hardware efficient and hardware-aware, with a particular focus on wiring ML algorithms directly into FPGA fabric, for a deterministic hardware computation.

    Go to contribution page
  20. 12. New AI Infrastructure for Dr.Sai Agents at IHEP
    Hong Wang
    26/05/2026, 16:00
  21. 26. Dr.Sai Agentic Scientific Workflow in JUNO
    Xuefeng Ding (Istitute of High Energy Physics, Chinese Academy of Sciences)
    26/05/2026, 16:45

    Modern neutrino experiments depend on complex and highly iterative analysis workflows involving reconstruction, simulation, calibration, background studies, validation, and documentation. In many cases, the bottleneck is not a single algorithm, but the efficient, reproducible, and auditable execution of expert-defined procedures. This talk presents the application of the Dr.Sai agentic...

    Go to contribution page
  22. 34. Morning Session [Chaired by Farouk Mokhtar]
    27/05/2026, 08:59
  23. 13. Jet tagging from DNN to Transformers
    Bingxuan Liu (Sun Yat-Sen University (CN))
    27/05/2026, 09:00
  24. 14. Jet tagging on the Edge
    Christopher Edward Brown (CERN)
    27/05/2026, 09:35
  25. 15. Anomaly Detection on the edge
    Maciej Mikolaj Glowacki (CERN)
    27/05/2026, 10:10
  26. 35. Morning Session 2 [Chaired by Jingjing Pan]
    27/05/2026, 11:14
  27. 25. Accelerating Multi-Latent Attention on Spatial Architectures
    Guojie Luo
    27/05/2026, 11:15

    Multi-latent attention (MLA) shrinks the KV cache but must rebuild per-head keys and values during decode, shifting the bottleneck to on-chip movement and orchestration. Spatial architectures, which consist of many-core tiles with local memory, explicit movers, and on-chip networks, therefore reward careful dataflow and mapping as much as computing. Unlike FPGA-centric stacks with long...

    Go to contribution page
  28. 19. Discussion
    27/05/2026, 11:50
  29. 36. Afternoon Session [Chaired by Chen Zhou]
    27/05/2026, 13:59
  30. 22. Agent for multiple loop calculation
    Xiang Li (Peking University)
    27/05/2026, 14:00
    Oral talks

    The LHC now delivers percent-level precision across Higgs, top, and electroweak observables, yet the corresponding multi-loop theory predictions—essential for converting experimental measurements into constraints on the Standard Model and new physics—remain locked behind formidable expertise barriers. A full NNLO or N$^3$LO calculation requires navigating a fragmented ecosystem of specialized...

    Go to contribution page
  31. 24. AI for future Higgs factory
    Yongfeng Zhu
    27/05/2026, 14:35
    Oral talks

    We present an AI-driven framework to enhance the physics reach of future electron–positron colliders through fine-grained jet understanding and holistic event analysis. We propose jet origin identification (JoI), which classifies jets into five quark species, their anti-quarks, and gluons. Using simulated $\nu\bar{\nu}H,\ H\rightarrow jj$ events at 240~GeV at the CEPC, the method achieves jet...

    Go to contribution page
  32. 28. Metric Spaces for Collider Events—Towards Scientific AI for Particle Physics
    Tianji Cai (SLAC National Accelerator Laboratory), Ms Tianji Cai (University of California, Santa Barbara)
    27/05/2026, 15:05

    As the Large Hadron Collider (LHC) generates hundreds of petabytes of data and even more with its high-luminosity upgrade, particle physics is entering a new era of data-driven discovery where Artificial Intelligence (AI) plays a pivotal role. Alongside numerous task-specific AI algorithms, recent works have introduced foundation models excelling across diverse applications. At the heart of...

    Go to contribution page
  33. 20. Potential of di-Higgs observation via a calibratable jet-free HH->4b framework
    Tianyi Yang (Peking University (CN))
    27/05/2026, 16:00

    We present a calibratable, jet-free framework that enhances the search significance of the flagship LHC channel HH→4b by more than a factor of five compared to existing approaches. The method employs a mass-decorrelated discriminant to identify h1h2→4b with variable h1,2 masses and a simultaneous estimator of (mh1,mh2), both derived from multiclass classification on all-particle inputs. The HH...

    Go to contribution page
  34. 17. Learning Detector-Level Probability Distributions with Sliced Wasserstein Distance
    Chucheng Pan (Wuhan University (CN))
    27/05/2026, 16:15
    Oral talks
    Lightening talks

    High-energy physics is intrinsically a field that relies on the accurate modeling and comparison of high-dimensional probability distributions, arising from complex detector responses and multi-body final states. The Sliced Wasserstein Distance (SWD) provides a powerful and computationally efficient loss function tailored for high-dimensional probability distributions. By projecting high...

    Go to contribution page
  35. 21. “Hadron-in-jet” AI tagging to detect rare decays
    Linrui Chen (Wuhan University)
    27/05/2026, 16:30

    We investigate a novel class of boosted-object signatures at the LHC, where a high-pT fat jet contains an identifiable hadron or quarkonium state originating from rare or semi-exclusive decays.

    Go to contribution page
  36. 16. Talks&Closing
    27/05/2026, 16:45
  37. 1. Quantum autoencoder for anomalous couplings
    shuai zhang (LNNU)
    Oral talks
    Lightening talks

    Given the success of the Standard Model (SM), any signals of physics beyond the Standard Model (NP) are expected to be small. Consequently, future searches for NP and precision tests of the SM will rely on high-luminosity collider experiments. The large volumes of data produced, together with the increased complexity of rare processes involving multiple final-state particles, pose significant...

    Go to contribution page