1

Multimarginal Flow Matching with Optimal Transport Potentials
A novel flow matching technique for inferring physical trajectories from observations snapshots, based on a physics-inspired modification of dynamic optimal transport. SOTA results on biological, meteorogical, and oceanographic datasets.
Raghav Kansal, David Crair, Nghia Nguyen, Scott Pope, Brad Parry
Cite
An Evaluation of Representation Learning Methods in Particle Physics Foundation Models
Michael Chen, Raghav Kansal, Abhijith Gandrakota, Zichun Hao, Jennifer Ngadiuba, Maria Spiropulu
PDF arXiv Cite
RINO: Renormalization Group Invariance with No Labels
A novel physics-informed self-supervised pretraining strategy for foundation models in physics. SOTA results on transfer learning between simulations and real data.
Zichun Hao, Raghav Kansal, Abhijith Gandrakota, Chang Sun, Jennifer Ngadiuba, Javier Duarte, Maria Spiropulu
PDF arXiv Cite Project
RINO: Renormalization Group Invariance with No Labels
Learning Symmetry-Independent Jet Representations via Jet-Based Joint Embedding Predictive Architecture
Subash Katel, Haoyang Li, Zihan Zhao, Raghav Kansal, Farouk Mokhtar, Javier Duarte
PDF arXiv Cite Project
Induced Generative Adversarial Particle Transformers
Anni Li, Venkat Krishnamohan, Raghav Kansal, Javier Duarte, Rounak Sen, Steven Tsan, Zhaoyu Zhang
PDF arXiv Cite Project
JetNet: A Python package for accessing open datasets and benchmarking machine learning methods in high energy physics
JetNet is a Python package that aims to increase accessibility and reproducibility for machine learning (ML) research in high energy …
Raghav Kansal, Carlos Pareja, Javier Duarte
PDF Cite Code Project
Do graph neural networks learn traditional jet substructure?
At the CERN LHC, the task of jet tagging, whose goal is to infer the origin of a jet given a set of final-state particles, is dominated …
Farouk Mokhtar, Raghav Kansal, Javier Duarte
PDF arXiv Cite Project Poster
Particle Cloud Generation with Message Passing Generative Adversarial Networks
Introduces the message-passing generative adversarial (MPGAN) model and JetNet dataset. We found the physics-informed MPGAN model outperformed all existing point-cloud GANs in simulating high momentum jets.
Raghav Kansal, Javier Duarte, Hao Su, Breno Orzari, Thiago Tomei, Maurizio Pierini, Mary Touranakou, Jean-Roch Vlimant, Dimitrios Gunopulos
PDF arXiv Cite Code Dataset Project
Particle Cloud Generation with Message Passing Generative Adversarial Networks
Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance
Autoencoders have useful applications in high energy physics in anomaly detection, particularly for jets - collimated showers of …
Steven Tsan, Raghav Kansal, Anthony Aportela, Daniel Diaz, Javier Duarte, Sukanya Krishna, Farouk Mokhtar, Jean-Roch Vlimant, Maurizio Pierini
PDF arXiv Cite Project Project Poster
Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance
Explaining machine-learned particle-flow reconstruction
Developed a graph neural network model to reconstruct particle collisions and interpreted the results using explainable AI techniques.
Farouk Mokhtar, Raghav Kansal, Daniel Diaz, Javier Duarte, Joosep Pata, Maurizio Pierini, Jean-Roch Vlimant
PDF arXiv Cite Project Project Poster
Explaining machine-learned particle-flow reconstruction