ML
Machine Learning for Science (ML4SCI) Umbrella Organization
Science and medicineMachine learning applications in science
Get involved
Links from the organization’s published listing (2026). Older contact links may have moved.
Proposal examples
Browse the proposal library →Outcomes are reported by the linked archives.
- 2025 · accepteddiffusion proposal hamees ↗
- 2026 · acceptedNeural Operators for Fast Simulation of Strong Gravitational Lensing Metrex-Nova ↗
- 2026 · acceptedPhysics-Informed Models for Squared Amplitude Calculation ↗
- 2026 · rejectedgsoc proposal arnav kapoor ↗
Programs & participation
6 records across 1 programIndexed project records; missing years are not zero. Coverage
2026Google Summer of CodeAnnual program · 33 projects indexed
- [DeepLense] Foundation Model for Gravitational Lensing - WaveLens-JEPA
- Agentic AI for Autonomous Gravitational Lensing Simulation Workflows
- Agentic Lagrangian Extraction from the Literature ML4SCI – HEPSIM5
- Brain-to-Brain Decoder: Leakage-Aware Validation and Interpretable CEBRA Mapping for Dyadic EEG
- Building and Comparing Segmentation Strategies for Coronary Artery Calcium CAC
- Data Augmentation Using Physics-Informed Plaque Growth Simulation
- Deep Graph Anomaly Detection with Contrastive Learning for New Physics Searches
- DeepLense: Lens Finding for LSST Images
- Event Classification With Masked Transformer Autoencoders
- Exoplanet Atmosphere Characterization
- EXXA - Denoising Astronomical Observations of Protoplanetary Disks
- Foundation models for End-to-End event reconstruction
- Foundation Models for Exoplanet Characterization
- Graph Representation Learning for Fast Detector Simulation
- Hybrid 3D CNN with Deformable Attention and FNO for CAC Segmentation
- Hybrid Quantum-Classical Representation Learning for Dark Matter Substructure Classification
- Linear Attention Vision Transformers for CMS End-to-End Jet Classification and Mass Regression
- Linear attention vision transformers for end to end mass regression and classification
- Machine Learning for Gravitational Lens Finding
- Neural Operators for Fast Simulation of Strong Gravitational Lensing
- Physics Guided Machine Learning on Real Gravitational Lensing Images
- Physics Informed Neural Network Diffusion Equation (PINNDE)
- Physics-Aware Super-Resolution of CMS Jet Images Using Transformer - Diffusion Architectures
- Physics-Informed Models for Squared Amplitude Calculation
- Physics-Informed Neural Network Diffusion Equation (PINNDE)
- Physics-Informed Neural Network Shape Optimization
- Quantum Circuit Design with LLMs
- Quantum Latent Diffusion Models for High-Resolution Simulation
- Quantum Resource Analysis and Benchmarking
- Quantum Sinusoidal Kolmogorov Arnold Networks for High Energy Physics
- Radiomics Feature Extraction and Calcium Phenotype Discovery
- Unsupervised Super-Resolution and Analysis of Real Lensing Images
- Using Next-Gen Transformers to Seed Generative Models for Symbolic Regression
Source checked Sep 28, 2026
Participation imported from the GSoC Organizations archive snapshot; this historical listing is not an application-status claim.
2025Google Summer of CodeAnnual program · 31 projects indexed
- A Diffusion-Based Deep Learning Framework for Denoising Protoplanetary Disk Observations
- A Self-Supervised, Physics-Informed Hybrid Transformer Framework for Multi-Tasks in HEP
- Building a Foundational Model for Symbolic Regression in High Energy Physics
- Continual learning for data quality monitoring
- Data Processing Pipeline for the LSST
- DeepLense: Gravitational Lens Finding Project
- Diffusion Models for Gravitational Lensing Simulation
- Discovering Hidden Symmetries in CMS Calorimetric Data via Semi-Supervised Learning
- Discovery of hidden symmetries and conservation laws
- Discovery of hidden symmetries and conservation laws
- Exoplanet Atmosphere Characterization
- Foundation Model for Gravitational Lensing
- Foundation models for End-to-End event reconstruction
- Foundation Models for Exoplanet Characterization
- Foundation models for symbolic regression tasks
- Graph Representation Learning for Fast Detector Simulation
- Implementation of Quantum Generative Adversarial Networks to Perform HEP Analysis at the LHC
- Latent Neural Signatures in Clinical vs. Neurotypical Dyads: A CEBRA Pipeline
- Neural Harmony – Decoding Social Interactions with CEBRA-based framework for analysing EEG data
- Next-Generation Transformer Models for Symbolic Calculations of Squared Amplitudes in HEP
- Physics Guided Machine Learning on Real Lensing Images
- Physics informed neural network diffusion equation
- Physics-Informed Performer for Symbolic Squared Amplitudes in HEP
- Q-MAML for Variational Quantum Algorithms for High Energy Physics Analysis at the LHC
- Quantum Diffusion Model for HEP
- Quantum Kolmogorov-Arnold Networks for High Energy Physics Analysis at the LHC
- Quantum Machine Learning For Exoplanet Characterization
- Quantum Particle transformer for High Energy Physics Analysis at the LHC
- State-space models for squared amplitude calculation in high-energy physics
- Super-Resolution and Analysis of Gravitational Lensing Images
- Unsupervised super-resolution and analysis of observed lensing images
Source checked Sep 28, 2026
Participation imported from the GSoC Organizations archive snapshot; this historical listing is not an application-status claim.
2024Google Summer of CodeAnnual program · 26 projects indexed
- Diffusion Models for Gravitational Lensing Simulation
- Equivariant quantum neural networks for High Energy Physics Analysis at the LHC
- Equivariant Vision Networks for Predicting Planetary Systems' Architectures
- Evolutionary and Transformer Models for Symbolic Regression
- Evolutionary and Transformer Models for Symbolic Regression
- Exoplanet Atmosphere Characterization
- Graph Neural Networks for Particle Momentum Estimation in the CMS Trigger System
- Implementation of Quantum Generative Adversarial Networks to Perform HEP Analysis at LHC
- Learning quantum representations of classical high energy physics data with contrastive learning
- Learning quantum representations of classical high energy physics data with contrastive learning
- Learning Representation Through Self-Supervised Learning on Real Gravitational Lensing Images
- Learning Representation Through Self-Supervised Learning on Real Gravitational Lensing Images
- Masked Auto-Encoders for Efficient E2E Particle Reconstruction & Compression for CMS Experiment
- Masked Auto-Encoders for End-to-End Particle Reconstruction and Compression for the CMS Experiment
- Non-local GNNs for Jet Classification
- Physics-Guided Machine Learning
- QMLHEP3: Learning quantum representations of classical HEP data with contrastive learning
- Quantum Diffusion Model for High Energy Physics
- Quantum Generative Adversarial Networks for Monte Carlo Simulations
- Quantum Graph Neural Networks for High Energy Physics Analysis at the LHC
- Quantum Graph Neural Networks for High Energy Physics Analysis at the LHC
- Quantum transformer for High Energy Physics Analysis at the LHC
- Resilient Physics-Informed Anomaly Detection and Inference of Lensing Images on Sparse Datasets
- Self-Supervised Learning for End-to-End Particle Reconstruction for the CMS Experiment
- Superresolution for Strong Gravitational Lensing
- Transformer Models for Symbolic Calculations of Squared Amplitudes in HEP
Source checked Sep 28, 2026
Participation imported from the GSoC Organizations archive snapshot; this historical listing is not an application-status claim.
2023Google Summer of CodeAnnual program · 23 projects indexed
- Deriving planetary surface composition from orbiting observations from spacecraft
- Diffusion Models for Fast Detector Simulation
- Equivariant Neural Networks for Dark Matter Morphology with Strong Gravitational Lensing
- Equivariant Quantum Neural Networks for Continuous Symmetry in High Energy Physics
- Exploring the underlying symmetries in particle physics with equivariant neural networks
- FASEROH : Building seq2seq model for mapping histograms to empirical symbolic representations
- Finding Exoplanets with Astronomical Observations
- Graph Neural Networks for End-to-End Particle Identification with the CMS Experiment
- Identifying the Physical Process of Planet Formation (EXXA)
- Invariant and Equivariant Quantum Graph Attention Transformers for HEP Analysis at the LHC
- Lensiformer: A Physics-Informed Vision Transformer Architecture for Dark Matter Morphology
- Prediction of High Energy Particle Kinematics via Masked Autoencoding
- Quantum Generative Adversarial Networks for HEP event generation the LHC
- Quantum Graph Neural Networks for High Energy Physics Analysis at the LHC
- Quantum transformer for High Energy Physics Analysis at the LHC
- Quantum Transformers for HEP Analysis at the LHC
- Self-Supervised Learning for Strong Gravitational Lensing
- Self-Supervised Learning for Strong Gravitational Lensing
- Super-Resolution for Strong Gravitational Lensing
- SYMBA - Symbolic empirical representation of squared amplitudes in high-energy physics
- Symbolic empirical representation of squared amplitudes in high-energy physics
- Updating the DeepLense Pipeline
- Vision Transformers for End-to-End Particle Reconstruction for the CMS Experiment
Source checked Sep 28, 2026
Participation imported from the GSoC Organizations archive snapshot; this historical listing is not an application-status claim.
2022Google Summer of CodeAnnual program · 20 projects indexed
- Anomalies Detection
- Deep Regression Exploration
- End-to-End Deep Learning Reconstruction for CMS Experiment
- Equivariant Transformers for Decoding Dark Matter with Strong Gravitational Lensing
- Fast Accurate Symbolic Empirical Representation of Histograms
- Finding Exoplanets with Astronomical Observations
- Finding Exoplanets with Astronomical Observations
- Finding Exoplanets with Astronomical Observations
- Graph Neural Networks for End-to-End Particle Identification with the CMS Experiment
- Graph Neural Networks for End-to-End Particle Identification with the CMS Experiment
- Gravitational Lens Finding for Dark Matter Substructure Pipeline
- Implementation of QGANs to Perform High Energy Physics Analysis at the LHC
- Quantum Convolutional Neural Networks for High Energy Physics Analysis at the LHC
- Quantum Generative Adversarial Neural Networks for High Energy Physics Analysis at the LHC
- Quantum Variational Autoencoders for HEP Analysis at the LHC
- Symbolic empirical representation of squared amplitudes in high-energy physics
- Transformers for Dark Matter Morphology with Strong Gravitational Lensing
- Transformers for Dark Matter Morphology with Strong Gravitational Lensing
- Updating the DeepLense Pipeline
- Vision Transformers for End-to-End Particle Reconstruction for the CMS Experiment
Source checked Sep 28, 2026
Participation imported from the GSoC Organizations archive snapshot; this historical listing is not an application-status claim.
2021Google Summer of CodeAnnual program · 19 projects indexed
- Background Estimation with Neural AutoRegressive Flows
- Background Estimation with Neural Autoregressive Flows Proposal
- Decoding quantum states through Nuclear Magnetic Resonance
- Dimensionality Reduction for Studying Diffuse Circumgalactic Medium
- Direct Objective Function for Anomaly Detection
- Domain Adaptation for Decoding Dark Matter with Strong Gravitational Lensing
- End-to-End Deep Learning Reconstruction for CMS Experiment
- End-to-End Deep Learning Regression for Measurements with the CMS Experiment
- Equivariant Neural Networks for Dark Matter Morphology with Strong Gravitational Lensing
- Graph Neural Networks for End-to-End Particle Identification with the CMS Experiment
- Graph Neural Networks for Particle Momentum Estimation in the CMS Trigger System
- Machine Learning for Turbulent Fluid Dynamics
- Machine Learning Model for the Albedo of Mercury
- Machine Learning Model for the Planetary Albedo
- Normalizing Flows for Fast Detector Simulation
- On the potential of graph-based models in High Energy Physics
- Quantum Convolutional Neural Networks for High-Energy Physics Analysis at the LHC
- Quple - Quantum GAN
- Uncovering the Enigma of Type-Ia Supernovae: Thermonuclear Supernova Classification via their Nuclear Signatures
Source checked Sep 28, 2026
Participation imported from the GSoC Organizations archive snapshot; this historical listing is not an application-status claim.