paper-with-me

Papers

PC-Droid: Faster diffusion and improved quality for particle cloud generation

2023-07-13 · Matthew Leigh, Debajyoti Sengupta, John Andrew Raine, Guillaume Quétant, Tobias Golling

Building on the success of PC-JeDi we introduce PC-Droid, a substantially improved diffusion model for the generation of jet particle clouds. By leveraging a new diffusion formulation, studying more recent integration solvers, and training on all jet types simultaneously, we are able to achieve state-of-the-art performance for all types of jets across all evaluation metrics. We study the trade-off between generation speed and quality by comparing two attention based architectures, as well as the potential of consistency distillation to reduce the number of diffusion steps. Both the faster architecture and consistency models demonstrate performance surpassing many competing models, with generation time up to two orders of magnitude faster than PC-JeDi and three orders of magnitude faster than Delphes.

📄 PDF Abstract BibTeX arXiv:2307.06836

Code (0)

등록된 구현이 없습니다.

Tasks

All

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics

2023-03-09 · Matthew Leigh, Debajyoti Sengupta, Guillaume Quétant, John Andrew Raine 외

In this paper, we present a new method to efficiently generate jets in High Energy Physics called PC-JeDi. This method utilises score-based diffusion models in conjunction with transformers which are well suited to the t…

Vocal Bursts Intensity Prediction

Tempered Guided Diffusion

2026-05-05 · Andreas Makris, Paul Fearnhead, Chris Nemeth arxiv

Training-free conditional diffusion provides a flexible alternative to task-specific conditional model training, but existing samplers often allocate computation inefficiently: independent guided trajectories can vary wi…

Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models

2026-02-02 · Ziwei Luo, Ziqi Jin, Lei Wang, Lidong Bing 외 arxiv

This work presents self-rewarding sequential Monte Carlo (SMC), an inference-time scaling algorithm enabling effective sampling of masked diffusion language models (MDLMs). Our algorithm stems from the observation that m…

EPiC-ly Fast Particle Cloud Generation with Flow-Matching and Diffusion

2023-09-29 · Erik Buhmann, Cedric Ewen, Darius A. Faroughy, Tobias Golling 외

Jets at the LHC, typically consisting of a large number of highly correlated particles, are a fascinating laboratory for deep generative modeling. In this paper, we present two novel methods that generate LHC jets as poi…

A General Framework for Inference-time Scaling and Steering of Diffusion Models

2025-01-12 · Raghav Singhal, Zachary Horvitz, Ryan Teehan, Mengye Ren 외

Diffusion models produce impressive results in modalities ranging from images and video to protein design and text. However, generating samples with user-specified properties remains a challenge. Recent research proposes…

Protein Design