# JetFormer: A Scalable and Efficient Transformer for Jet Tagging from Offline Analysis to FPGA Triggers

arXiv: https://arxiv.org/abs/2601.17215 · HTML: https://mlsanity.com/paper/2601.17215/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 23 Jan 2026.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets](https://mlsanity.com/paper/1903.05662/) (2019)
- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [BitNet: Scaling 1-bit Transformers for Large Language Models](https://mlsanity.com/paper/2310.11453/) (2023)
- [Fast inference of deep neural networks in FPGAs for particle physics](https://mlsanity.com/paper/1804.06913/) (2018)
- [Structured Pruning for Deep Convolutional Neural Networks: A survey](https://mlsanity.com/paper/2303.00566/) (2023)
- [Particle Transformer for Jet Tagging](https://mlsanity.com/paper/2202.03772/) (2022)
- [Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors](https://mlsanity.com/paper/2006.10159/) (2020)
- [Fast convolutional neural networks on FPGAs with hls4ml](https://mlsanity.com/paper/2101.05108/) (2021)
- [Allo: A Programming Model for Composable Accelerator Design](https://mlsanity.com/paper/2404.04815/) (2024)
- [Ultra-low latency recurrent neural network inference on FPGAs for physics applications with hls4ml](https://mlsanity.com/paper/2207.00559/) (2022)
- [LL-GNN: Low Latency Graph Neural Networks on FPGAs for High Energy Physics](https://mlsanity.com/paper/2209.14065/) (2022)
- [Ultrafast jet classification on FPGAs for the HL-LHC](https://mlsanity.com/paper/2402.01876/) (2024)
- [Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml](https://mlsanity.com/paper/2205.07690/) (2022)
- [HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs](https://mlsanity.com/paper/2405.00645/) (2024)
- [Fast Jet Tagging with MLP-Mixers on FPGAs](https://mlsanity.com/paper/2503.03103/) (2025)
- [da4ml: Distributed Arithmetic for Real-time Neural Networks on FPGAs](https://mlsanity.com/paper/2507.04535/) (2025)
- [Ultra Fast Transformers on FPGAs for Particle Physics Experiments](https://mlsanity.com/paper/2402.01047/) (2024)
- [Sub-microsecond Transformers for Jet Tagging on FPGAs](https://mlsanity.com/paper/2510.24784/) (2025)
- [Low Latency Transformer Inference on FPGAs for Physics Applications with hls4ml](https://mlsanity.com/paper/2409.05207/) (2024)
- [Spatially Aware Linear Transformer (SAL-T) for Particle Jet Tagging](https://mlsanity.com/paper/2510.23641/) (2025)

## Built on by (most cited first, 3 of 3)

- [HGQ-LUT: Fast LUT-Aware Training and Efficient Architectures for DNN Inference](https://mlsanity.com/paper/2604.22293/) (2026)
- [Patch Hierarchical Attention Transformer for Efficient Particle Jet Tagging](https://mlsanity.com/paper/2605.21789/) (2026)
- [Machine learning for the LHC physics program: a 2025-2026 stocktake](https://mlsanity.com/paper/2609.32874/) (2026)

## Abstract (arXiv)

We present JetFormer, a versatile and scalable encoder-only Transformer architecture for particle jet tagging at the Large Hadron Collider (LHC). Unlike prior approaches that are often tailored to specific deployment regimes, JetFormer is designed to operate effectively across the full spectrum of jet tagging scenarios, from high-accuracy offline analysis to ultra-low-latency online triggering. The model processes variable-length sets of particle features without relying on input of explicit pairwise interactions, yet achieves competitive or superior performance compared to state-of-the-art methods. On the large-scale JetClass dataset, a large-scale JetFormer matches the accuracy of the interaction-rich ParT model (within 0.7%) while using 37.4% fewer FLOPs, demonstrating its computational efficiency and strong generalization. On benchmark HLS4ML 150P datasets, JetFormer consistently outperforms existing models such as MLPs, Deep Sets, and Interaction Networks by 3-4% in accuracy. To bridge the gap to hardware deployment, we further introduce a hardware-aware optimization pipeline based on multi-objective hyperparameter search, yielding compact variants like JetFormer-tiny suitable for FPGA-based trigger systems with sub-microsecond latency requirements. Through structured pruning and quantization, we show that JetFormer can be aggressively compressed with minimal accuracy loss. By unifying high-performance modeling and deployability within a single architectural framework, JetFormer provides a practical pathway for deploying Transformer-based jet taggers in both offline and online environments at the LHC. Code is available at https://github.com/walkieq/JetFormer.