Summary of GSoC 2026 Projects and Supervisors

Full List of Proposals

Agentic AI for Autonomous Gravitational Lensing Simulation Workflows
Agentic AI for High Energy Physics Analyses at the CMS Detector
Agentic AI for High Energy Physics Data Quality Monitoring
Agentic Exclusion Limit Extraction
Agentic Lagrangian Extraction from the Literature
Automated Scientific Discovery of Quantum Machine Learning Architectures
Brain-to-Brain Decoder - Validating Neural Synchrony Patterns in Human Conversation
Building and Comparing Segmentation Strategies for Coronary Artery Calcium (CAC)
Data Augmentation Using Physics-Informed Plaque Growth Simulation
Data Processing Pipeline for the LSST
Deep Graph anomaly detection with contrastive learning for new physics searches
Deep Learning Inference for mass regression
Denoising Astronomical Observations of Protoplanetary Disks
Diffusion Models for Fast Detector Simulation
Diffusion models for fast and accurate simulations of low level CMS experiment data.
Discovery of hidden symmetries and conservation laws
End-to-End event classification with sparse neural networks
End-to-End particle collision track reconstruction
Equivariant Vision Networks for Predicting Planetary Systems’ Architectures
Equivariant quantum neural networks for High Energy Physics Analysis at the LHC
Event Classification With Masked Transformer Autoencoders
Exoplanet Atmosphere Characterization
Fast Accurate Symbolic Empirical Representation Of Histograms
Foundation Model for Gravitational Lensing
Foundation Models for Exoplanet Characterization
Foundation Models for Squared Amplitude Calculation
Foundation models for End-to-End event reconstruction
Graph Representation Learning for Fast Detector Simulation
Graph Transformers for Fast Detector Simulation
Gravitational Lens Finding
Hybrid Quantum-Classical Representation Learning for Dark Matter Substructure Classification
Implementation of Quantum Generative Adversarial Networks to Perform High Energy Physics Analysis at the LHC
Jet Observable Library for Monte Carlo Validation
LM-JEPA for Squared Amplitude Calculation
LM-JEPA for Symbolic Regression
Learning Parametrization with Implicit Neural Representations
Learning quantum representations of classical high energy physics data with contrastive learning
Learning the Latent Structure with Diffusion Models
Linear attention vision transformers for end to end mass regression and classification
ML-Based Simulation Bias Analysis - Pythia vs Herwig vs Data
Neural Operators for Fast Simulation of Strong Gravitational Lensing
Non-local GNNs for Jet Classification
Optimal Transport in High Energy Physics
Physics Guided Machine Learning on Real Lensing Images
Physics-Informed Diffusion Models for Gravitational Lensing Simulation
Physics-Informed Encoding and Decoding for Squared Amplitude Calculation
Physics-Informed Models for Squared Amplitude Calculation
Physics-Informed Neural Network Diffusion Equation (PINNDE)
Physics-Informed Neural Network Diffusion Equation (PINNDE)
Physics-informed neural network shape optimization
Q-MAML - Quantum Model-Agnostic Meta-Learning for Variational Quantum Algorithms for High Energy Physics Analysis at the LHC
Quantum Circuit Design with LLMs
Quantum Diffusion Model for High Energy Physics
Quantum Foundation Model for High Energy Physics
Quantum Graph Neural Networks for High Energy Physics Analysis at the LHC
Quantum Kolmogorov-Arnold Networks for High Energy Physics Analysis at the LHC
Quantum Machine Learning for Exoplanet Characterization
Quantum Machine Learning for Exoplanet Characterization
Quantum Particle transformer for High Energy Physics Analysis at the LHC
Quantum Reinforcement Learning for High Energy Physics
Quantum Resource Analysis and Benchmarking
Quantum transformer for High Energy Physics Analysis at the LHC
Radiomics Feature Extraction and Calcium Phenotype Discovery
Semi-supervised Symmetry Discovery
Super resolution at the CMS detector
Super resolution at the CMS detector
Symbolic Regression for Observable Event-Level Reweighting
Titans for Squared Amplitude Calculation
Unsupervised Super-Resolution and Analysis of Real Lensing Images
Using Next-Gen Transformers to Seed Generative Models for Symbolic Regression