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

Diffusion-based classifiers such as those relying on the Personalized PageRank and the Heat kernel, enjoy remarkable classification accuracy at modest computational requirements. Their performance however is affected by the extent to which…

Voxel-wise dose prediction is a critical yet challenging task in practical radiotherapy (RT) planning, as bespoke models trained from scratch often struggle to generalize across diverse clinical settings. Meanwhile, generative models…

Calorimeter shower simulations are often the bottleneck in simulation time for particle physics detectors. A lot of effort is currently spent on optimizing generative architectures for specific detector geometries, which generalize poorly.…

Text-to-image (T2I) models have recently experienced rapid development, achieving astonishing performance in terms of fidelity and textual alignment capabilities. However, given a long paragraph (up to 512 words), these generation models…

Simulations of particle showers in calorimeters are computationally time-consuming, as they have to reproduce both energy depositions and their considerable fluctuations. A new approach to ultra-fast simulations are generative models where…

The physics programs of current and future collider experiments necessitate the development of surrogate simulators for calorimeter showers. While much progress has been made in the development of generative models for this task, they have…

Feature caching has emerged as an effective strategy to accelerate diffusion transformer (DiT) sampling through temporal feature reuse. It is a challenging problem since (1) Progressive error accumulation from cached blocks significantly…

The CALICE collaboration has constructed highly granular electromagnetic and hadronic calorimeter prototypes to evaluate technologies for the use in detector systems at a future Linear Collider. The hadron calorimeter uses small…

Diffusion models learn strong image priors that can be leveraged to solve inverse problems like medical image reconstruction. However, for real-world applications such as 3D Computed Tomography (CT) imaging, directly training diffusion…

The existing CMS endcap calorimeters will be replaced with a High Granularity Calorimeter (HGCAL) for operation at the High Luminosity (HL) LHC. Radiation hardness and excellent physics performance will be achieved by utilising silicon pad…

Diffusion models have revolutionized generative tasks, especially in the domain of text-to-image synthesis; however, their iterative denoising process demands substantial computational resources. In this paper, we present a novel…

Recent studies have revealed that, during the inference on generative AI models such as transformer, the importance of different weights exhibits substantial context-dependent variations. This naturally manifests a promising potential of…

Autoregressive (AR) modeling, known for its next-token prediction paradigm, underpins state-of-the-art language and visual generative models. Traditionally, a ``token'' is treated as the smallest prediction unit, often a discrete symbol in…

Video saliency prediction aims to identify the regions in a video that attract human attention and gaze, driven by bottom-up features from the video and top-down processes like memory and cognition. Among these top-down influences, language…

Foundation models (FM) have transformed computational pathology but remain computationally prohibitive for clinical deployment due to their massive parameter counts and high-magnification processing requirements. Here, we introduce XMAG, a…

We investigate the role of representations and architectures for classifying 3D shapes in terms of their computational efficiency, generalization, and robustness to adversarial transformations. By varying the number of training examples and…

In this study, we firstly introduce a method that converts CityGML data into voxels which works efficiently and fast in high resolution for large scale datasets such as cities but by sacrificing some building details to overcome the…

Diffusion Transformers have emerged as the foundation for vision generative models, but their scalability is limited by the high cost of hyperparameter (HP) tuning at large scales. Recently, Maximal Update Parametrization ($\mu$P) was…

Generative diffusion models have shown empirical successes in point cloud resampling, generating a denser and more uniform distribution of points from sparse or noisy 3D point clouds by progressively refining noise into structure. However,…

Recent advances in sparse voxel representations have significantly improved the quality of 3D content generation, enabling high-resolution modeling with fine-grained geometry. However, existing frameworks suffer from severe computational…