Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.12011 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911674175324160 |
|---|---|
| author | Huang, Zhengkun Sun, Gongxing |
| author_facet | Huang, Zhengkun Sun, Gongxing |
| contents | High-granularity calorimeters make ML-based fast shower simulation a high-dimensional generative modeling problem, where voxel-space generators must balance physics fidelity with training and inference cost. This work studies large-patch tokenization with x-prediction, enabling efficient raw voxel generation. We propose CaloArt, a modernized DiT-style backbone with 3D positional encoding and architectural refinements, trained via conditional flow matching with decoupled prediction and loss spaces. On CaloChallenge Dataset 2, where small patch size remains affordable, v-prediction performs well, and CaloArt achieves the best FPD, strongest high-level metrics, and strongest ResNet classifier metrics. On CaloChallenge Dataset 3, the 40500-voxel grid makes large patches necessary; x-prediction improves all reported metrics over v-prediction and places CaloArt on the quality-generation-time Pareto frontier. The final CCD2 and CCD3 models both retain O(10) ms single-GPU generation time, with 9.71 and 11.14 ms per shower. These results support large-patch voxel-space diffusion transformers with x-prediction as a compute-efficient route to high-granularity calorimeter shower synthesis, reducing training and inference cost without a pretrained latent tokenizer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_12011 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CaloArt: Large-Patch x-Prediction Diffusion Transformers for High-Granularity Calorimeter Shower Generation Huang, Zhengkun Sun, Gongxing Instrumentation and Detectors High Energy Physics - Experiment High Energy Physics - Phenomenology High-granularity calorimeters make ML-based fast shower simulation a high-dimensional generative modeling problem, where voxel-space generators must balance physics fidelity with training and inference cost. This work studies large-patch tokenization with x-prediction, enabling efficient raw voxel generation. We propose CaloArt, a modernized DiT-style backbone with 3D positional encoding and architectural refinements, trained via conditional flow matching with decoupled prediction and loss spaces. On CaloChallenge Dataset 2, where small patch size remains affordable, v-prediction performs well, and CaloArt achieves the best FPD, strongest high-level metrics, and strongest ResNet classifier metrics. On CaloChallenge Dataset 3, the 40500-voxel grid makes large patches necessary; x-prediction improves all reported metrics over v-prediction and places CaloArt on the quality-generation-time Pareto frontier. The final CCD2 and CCD3 models both retain O(10) ms single-GPU generation time, with 9.71 and 11.14 ms per shower. These results support large-patch voxel-space diffusion transformers with x-prediction as a compute-efficient route to high-granularity calorimeter shower synthesis, reducing training and inference cost without a pretrained latent tokenizer. |
| title | CaloArt: Large-Patch x-Prediction Diffusion Transformers for High-Granularity Calorimeter Shower Generation |
| topic | Instrumentation and Detectors High Energy Physics - Experiment High Energy Physics - Phenomenology |
| url | https://arxiv.org/abs/2605.12011 |