31 August 2026 to 4 September 2026
US/Pacific timezone
All in-person registration fee waivers have now been claimed.

ErwinParT: A Radially-Partitioned Hierarchical Transformer for Ultra-Low Latency Jet Tagging at the CMS Level-1 Trigger

31 Aug 2026, 17:36
1h 30m

Speaker

Vaibhav Lohia

Description

Real-time identification of jets from boosted heavy particles is vital for the High-Luminosity LHC physics program at CMS. However, deploying highly expressive architectures like the Particle Transformer within the hardware-constrained Level-1 (L1) trigger is severely limited by the quadratic scaling $\mathcal{O}(N^2)$ of standard self-attention. This computational burden makes microsecond-scale execution on Field Programmable Gate Arrays (FPGAs) resource-prohibitive. We present ErwinParT, a hierarchical transformer architecture designed for real-time edge deployment through a physics-informed structural partitioning scheme optimized for maximum hardware efficiency.
ErwinParT leverages the conical topology of high-energy jets by sorting constituent particles by their angular separation $\Delta R$ relative to the jet axis. This sequencing preserves spatial locality in the initial index mapping. The sorted constituents are then clustered into localized, fixed-size partitions ("balls"). Computing multi-head self-attention exclusively within these small neighborhoods mitigates the quadratic scaling bottleneck through an $\mathcal{O}(N \cdot B)$ formulation, where B is the bounded partition size. To retain the fine-grained substructure features needed for robust jet discrimination, the model incorporates Relative Position Embeddings (RPE) based on coordinate offsets from each partition’s center of mass, along with a distance-based attention bias that enforces continuous spatial decay.
Global context is recovered across the entire jet through an alternating cross-ball interaction mechanism akin to shifted window configurations. Systematically shifting the partition boundaries between consecutive transformer layers allows adjacent radial zones to exchange features. This establishes a global receptive field over the full depth of the network while bypassing the information bottlenecks typical of aggressive down-sampling architectures.
By design, this optimized ‭$\mathcal{O}(N \cdot B)$‬‭‬‭‬‭‬‭‬ formulation is structured to map naturally onto the hardware layer of CMS L1 trigger FPGAs as parallel, deterministic compute loops. Replacing all-to-all quadratic attention matrices with segmented, fixed-size matrix blocks is expected to significantly reduce Digital Signal Processor (DSP) and Block RAM (BRAM) utilization. This architectural alignment aims to yield a predictable, low-clock-cycle pipeline depth, making high-fidelity transformer inference a viable candidate for the sub-microsecond real-time data acquisition stream of the CMS experiment.

Do you plan to submit a 4-page extended abstract on OpenReview (only for Presentations/Posters)? Maybe

Authors

Aaron Wang Abhijith Gandrakota (Fermi National Accelerator Lab. (US)) Javier Mauricio Duarte (Univ. of California San Diego (US)) Rick Cavanaugh (University of Illinois at Chicago (US)) Vaibhav Lohia Zihan Zhao (Univ. of California San Diego (US))

Presentation materials

There are no materials yet.