Related papers: CaloArt: Large-Patch x-Prediction Diffusion Transf…

We present ShaDDR, an example-based deep generative neural network which produces a high-resolution textured 3D shape through geometry detailization and conditional texture generation applied to an input coarse voxel shape. Trained on a…

The Large Hadron Collider's high luminosity era presents major computational challenges in the analysis of collision events. Large amounts of Monte Carlo (MC) simulation will be required to constrain the statistical uncertainties of the…

This work aims to improve the efficiency of text-to-image diffusion models. While diffusion models use computationally expensive UNet-based denoising operations in every generation step, we identify that not all operations are equally…

Modern particle physics experiments face an increasing demand for high-fidelity detector simulation as luminosities rise and computational requirements approach the limits of available resources. Deep generative models have emerged as…

Particle identification (PID) is essential for future particle physics experiments such as the Circular Electron-Positron Collider and the Future Circular Collider. A high-granularity Time Projection Chamber (TPC) not only provides precise…

Recent Diffusion Transformers (e.g., DiT) have demonstrated their powerful effectiveness in generating high-quality 2D images. However, it is still being determined whether the Transformer architecture performs equally well in 3D shape…

Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs. To address this problem, feature caching methods have been introduced to accelerate diffusion…

Monte Carlo simulations are essential for physics analyses in high-energy physics, but their computational demands are continuously increasing. In LHCb, 90 % of computing resources are used for simulations, with the calorimeter simulation…

The CALICE collaboration is developing highly granular calorimeters for experiments at a future lepton collider primarily to establish technologies for particle flow event reconstruction. These technologies also find applications elsewhere,…

Recent advancements in camera-based occupancy prediction have focused on the simultaneous prediction of 3D semantics and scene flow, a task that presents significant challenges due to specific difficulties, e.g., occlusions and unbalanced…

To achieve state-of-the-art jet energy resolution for Particle Flow, sophisticated energy clustering algorithms must be developed that can fully exploit available information to separate energy deposits from charged and neutral particles.…

The speed and fidelity of detector simulations in particle physics pose compelling questions about LHC analysis and future colliders. The sparse high-dimensional data, combined with the required precision, provide a challenging task for…

In this work, we show that the impact of model capacity varies across timesteps: it is crucial for the early and late stages but largely negligible during the intermediate stage. Accordingly, we propose FlowBlending, a stage-aware…

In order to extend the direct observation of high-energy cosmic rays up to the PeV region, highly performing calorimeters with large geometrical acceptance and high energy resolution are required. Within the constraint of the total mass of…

The most advanced text-to-image (T2I) models require significant training costs (e.g., millions of GPU hours), seriously hindering the fundamental innovation for the AIGC community while increasing CO2 emissions. This paper introduces…

Flame tomography is a compelling approach for extracting large amounts of data from experiments via 3-D thermochemical reconstruction. Recent efforts employing neural-network flame representations have suggested improved reconstruction…

Among metal additive manufacturing technologies, powder-bed fusion features very thin layers and rapid solidification rates, leading to long build jobs and a highly localized process. Many efforts are being devoted to accelerate simulation…

We investigate methods to reduce inference time and memory footprint in stable diffusion models by introducing lightweight decoders for both image and video synthesis. Traditional latent diffusion pipelines rely on large Variational…

Point clouds captured by different sensors such as RGB-D cameras and LiDAR possess non-negligible domain gaps. Most existing methods design different network architectures and train separately on point clouds from various sensors.…

A silicon-based fine granularity calorimeter is a potential technology for the future International Linear Collider ILC, the future circular collider CEPC, and is also the chosen technology for the upgraded CMS experiment of the Large…