PLuM multimodal transformer improves top and H->bb jet tagging by jointly processing particle constituents and Lund plane splittings, yielding 25% higher background rejection at 25% di-Higgs efficiency.
hub
Dynamic Graph CNN for Learning on Point Clouds
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
abstract
Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices. While hand-designed features on point clouds have long been proposed in graphics and vision, however, the recent overwhelming success of convolutional neural networks (CNNs) for image analysis suggests the value of adapting insight from CNN to the point cloud world. Point clouds inherently lack topological information so designing a model to recover topology can enrich the representation power of point clouds. To this end, we propose a new neural network module dubbed EdgeConv suitable for CNN-based high-level tasks on point clouds including classification and segmentation. EdgeConv acts on graphs dynamically computed in each layer of the network. It is differentiable and can be plugged into existing architectures. Compared to existing modules operating in extrinsic space or treating each point independently, EdgeConv has several appealing properties: It incorporates local neighborhood information; it can be stacked applied to learn global shape properties; and in multi-layer systems affinity in feature space captures semantic characteristics over potentially long distances in the original embedding. We show the performance of our model on standard benchmarks including ModelNet40, ShapeNetPart, and S3DIS.
hub tools
representative citing papers
An XFEL Compton gamma-gamma collider at 125 GeV with a set transformer deep learning classifier on particle-flow point clouds can achieve high-precision Higgs measurements across hadronic, semi-leptonic, and leptonic final states including H to strange quarks.
Graph Kernel Networks learn PDE solution operators that generalize across discretization methods and grid resolutions using graph-based kernel integration.
PyTorch Geometric is a PyTorch library that delivers fast graph neural network training through sparse GPU kernels and variable-size mini-batching.
Point-cloud ML models classify charm- and bottom-origin electrons at ~80% purity for 40% efficiency, outperforming a BDT baseline, with performance limited by intrinsic decay similarity.
First NLO-QCD amplitude-assisted ML regression for longitudinal-boson production rate in di-boson events at the LHC, benchmarked against random forests.
Quadric loss combined with Chamfer loss yields better sharp-feature reconstruction in 3D models than either loss alone or other point-surface alternatives.
A classification-routed pipeline segments partial and full intraoral scans then retrieves and fits crown proposals from neighboring teeth embeddings, reporting macro DSC 0.9249 on 1958 partial scans.
An edge-weighted multi-graph GNN (E-PCN/KIGNet) that encodes four jet kinematic variables improves JetClass jet-tagging accuracy and attributes most predictions to angular separation and transverse momentum.
A specialized loss mitigates hubness bias in 3D zero-shot learning and sets new state-of-the-art results on ModelNet40, ModelNet10, McGill, and SHREC2015 for both ZSL and GZSL.
Introduces PCT using graph inception networks on voxels to represent large-scale 3D point clouds and reports outperformance on LiDAR sweeps for autonomous driving.
Explainability techniques applied to LundNet show that assigned node importance correlates with classical jet substructure observables such as N-subjettiness ratios and energy correlation functions, with shifts across transverse-momentum regimes.
Synthetic data can partially substitute for real data in object detection training, with performance tied to domain similarity and the volume of real data included.
Four extensions to FOOTPASS baselines for player-centric ball-action spotting in soccer videos achieve 0.548 Macro F1 on test set and 0.446 on challenge set.
citing papers explorer
-
Particle-Lund Multimodality in Jet Taggers
PLuM multimodal transformer improves top and H->bb jet tagging by jointly processing particle constituents and Lund plane splittings, yielding 25% higher background rejection at 25% di-Higgs efficiency.
-
Higgs Physics with the XFEL Compton $\boldsymbol{\gamma\gamma}$ Collider Concept at $\boldsymbol{\sqrt{s}=125}$ GeV
An XFEL Compton gamma-gamma collider at 125 GeV with a set transformer deep learning classifier on particle-flow point clouds can achieve high-precision Higgs measurements across hadronic, semi-leptonic, and leptonic final states including H to strange quarks.
-
Neural Operator: Graph Kernel Network for Partial Differential Equations
Graph Kernel Networks learn PDE solution operators that generalize across discretization methods and grid resolutions using graph-based kernel integration.
-
Fast Graph Representation Learning with PyTorch Geometric
PyTorch Geometric is a PyTorch library that delivers fast graph neural network training through sparse GPU kernels and variable-size mini-batching.
-
Heavy-Flavor Electron Classification Using Hadronic Environment as Point Cloud
Point-cloud ML models classify charm- and bottom-origin electrons at ~80% purity for 40% efficiency, outperforming a BDT baseline, with performance limited by intrinsic decay similarity.
-
Higher-order effects in amplitude-assisted polarisation extraction with machine-learning techniques
First NLO-QCD amplitude-assisted ML regression for longitudinal-boson production rate in di-boson events at the LHC, benchmarked against random forests.
-
Learning Embedding of 3D models with Quadric Loss
Quadric loss combined with Chamfer loss yields better sharp-feature reconstruction in 3D models than either loss alone or other point-surface alternatives.
-
From Full and Partial Intraoral Scans to Crown Proposal: A Classification-Guided Restoration Assistance Pipeline
A classification-routed pipeline segments partial and full intraoral scans then retrieves and fits crown proposals from neighboring teeth embeddings, reporting macro DSC 0.9249 on 1958 partial scans.
-
KIGNet: Physics-Motivated Multi-Graph Representation Learning for Explainable Jet Tagging
An edge-weighted multi-graph GNN (E-PCN/KIGNet) that encodes four jet kinematic variables improves JetClass jet-tagging accuracy and attributes most predictions to angular separation and transverse momentum.
-
Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects
A specialized loss mitigates hubness bias in 3D zero-shot learning and sets new state-of-the-art results on ModelNet40, ModelNet10, McGill, and SHREC2015 for both ZSL and GZSL.
-
Large-scale 3D point cloud representations via graph inception networks with applications to autonomous driving
Introduces PCT using graph inception networks on voxels to represent large-scale 3D point clouds and reports outperformance on LiDAR sweeps for autonomous driving.
-
Explainable AI for Jet Tagging: A Comparative Study of GNNExplainer, GNNShap, and GradCAM for Jet Tagging in the Lund Jet Plane
Explainability techniques applied to LundNet show that assigned node importance correlates with classical jet substructure observables such as N-subjettiness ratios and energy correlation functions, with shifts across transverse-momentum regimes.
-
How much real data do we actually need: Analyzing object detection performance using synthetic and real data
Synthetic data can partially substitute for real data in object detection training, with performance tied to domain similarity and the volume of real data included.
-
SoccerNet 2026 Player-Centric Ball-Action Spotting:Retraining and Post-Processing Extensions to the FOOTPASS Baselines
Four extensions to FOOTPASS baselines for player-centric ball-action spotting in soccer videos achieve 0.548 Macro F1 on test set and 0.446 on challenge set.