Related papers: GLOW: A Unified Particle Flow Transformer

In this paper, we present a comprehensive theoretical comparison of diffusion and flow matching under the Generator Matching framework. Despite their apparent differences, both diffusion and flow matching can be viewed under the unified…

Simulating trajectories of dynamical systems is a fundamental problem in a wide range of fields such as molecular dynamics, biochemistry, and pedestrian dynamics. Machine learning has become an invaluable tool for scaling physics-based…

Flow-based generative modeling is a powerful tool for solving inverse problems in physical sciences that can be used for sampling and likelihood evaluation with much lower inference times than traditional methods. We propose to refine flows…

Recent studies have demonstrated the effectiveness of Gated Linear Units (GLU) in enhancing transformer models, particularly in Large Language Models (LLMs). Additionally, utilizing a parallel configuration within each Transformer block…

Multimodal learning faces a fundamental tension between deep, fine-grained fusion and computational scalability. While cross-attention models achieve strong performance through exhaustive pairwise fusion, their quadratic complexity is…

We explore the use of normalizing flows to emulate Monte Carlo detector simulations of photon showers in a high-granularity electromagnetic calorimeter prototype for the International Large Detector (ILD). Our proposed method -- which we…

In this paper, we present an analogy for a power system dominated by grid-forming (GFM) sources that proves to be a powerful visualization tool for analyses of power flow, frequency regulation, and power dispatch. Frequency droop…

Accurate polyp segmentation remains challenging due to irregular lesion morphologies, ambiguous boundaries, and heterogeneous imaging conditions. While U-Net variants excel at local feature fusion, they often lack explicit mechanisms to…

Generative models have become increasingly powerful tools for robot motion generation, enabling flexible and multimodal trajectory generation across various tasks. Yet, most existing approaches remain limited in handling multiple types of…

Shape reconstruction techniques using structured light have been widely researched and developed due to their robustness, high precision, and density. Because the techniques are based on decoding a pattern to find correspondences, it…

The success of a specific neural network architecture is closely tied to the dataset and task it tackles; there is no one-size-fits-all solution. Thus, considerable efforts have been made to quickly and accurately estimate the performances…

We present UniFluid, a unified autoregressive framework for joint visual generation and understanding leveraging continuous visual tokens. Our unified autoregressive architecture processes multimodal image and text inputs, generating…

Dynamic GNN inference has exhibited effectiveness in High Energy Physics (HEP) experiments at High Luminosity Large Hadron Collider (HL-LHC) due to strong capability to model complex particle interactions in collision events. Future HEP…

Computational tools for rigorously verifying the performance of large-scale machine learning (ML) models have progressed significantly in recent years. The most successful solvers employ highly specialized, GPU-accelerated branch and bound…

This paper demonstrates particle tracking velocimetry performed for a model system wherein particle-laden liquid metal flow about a cylindrical obstacle was studied. We present the image processing methodology developed for particle…

Point cloud upsampling aims to generate dense point clouds from given sparse ones, which is a challenging task due to the irregular and unordered nature of point sets. To address this issue, we present a novel deep learning-based model,…

We tackle the task of scene flow estimation from point clouds. Given a source and a target point cloud, the objective is to estimate a translation from each point in the source point cloud to the target, resulting in a 3D motion vector…

Estimating three-dimensional conformations of a molecular graph allows insight into the molecule's biological and chemical functions. Fast generation of valid conformations is thus central to molecular modeling. Recent advances in…

The current developments for future electron-positron colliders are driven by the Particle Flow concept. In these developments, high granularity calorimeters play a central role. This presentation will focus on a new Particle Flow Algorithm…

Transformers are a popular choice for classification tasks and as backbones for object detection tasks. However, their high latency brings challenges in their adaptation to lightweight object detection systems. We present an approximation…