Sean Moran

✉ sean.j.moran@gmail.com

London

Hello 👋

I'm currently an AI/ML Director focused on Generative AI at JP Morgan Chase, where I lead the development of AI-driven solutions for Global Technology use-cases (Cybersecurity, Infrastructure Platforms, Cloud, SDLC, Data). My passion lies in solving applied AI problems that are deployed into production, delivering tangible value to both customers and the business. I specialize in tackling complex challenges that demand innovative thinking, with expertise spanning computer vision, natural language processing, and information retrieval.

I'm an AWS Certified Cloud Practitioner, a AWS Certified Data Engineer Associate, and a proud alumnus of the EdinburghNLP group.


Podcast on Latest Research Contributions (~15 minutes)

Side Projects and Resources

The LLM Bible: A comprehensive Large Language Model paper resource, searchable and user-friendly, currentrly indexing over 10,000 papers.

Awesome Papers on Learning to Hash: The largest collection of Approximate Nearest Search papers on the web, now with over 1,500 indexed.

Learning to Hash — Finding the Needle in the Haystack with AI

I used LLMs to Analyse The Cryptocurrency Market. These are my Lessons Learnt

ECCV 2020 Conference Certificate (high-quality reviews)

Senatus AI: Software Development Re-invented

Patents Granted

I’ve collaborated on filing numerous patents, primarily focused on AI innovations. Below is a selection:

A Device and Method for Image Processing — An image processing device for transforming an image. Sean Moran et al. (2021).

Image Processor — An image processing module implementing a multi-part trained AI model. Sean Moran et al. (2020).

Noise Estimation — Processing image data to detect stochastic noise and form a noise estimate. Sean Moran et al. (2020).

Image Processor — A processor with multiple modules working in series to refine raw images from a camera. Sean Moran et al. (2020).

Opensource Releases

API-Miner: AI that searches for similar API contract specification documents.

CryptoPanda: Leveraging GPT4o to analyse data from the Cryptocurrency market to detect the onset of price surges.

Topical: AI that learns to tag code repositories with descriptivie keywords.

Spam-T5: AI that learns to distinguish spam from ham e-mails.

CV4Code: AI that learns sourcecode feature representations using the vision transformer.

DeepLPF: AI that learns parametric filters for image enhancement.

CURL: AI that learns adjustable curves for image enhancement.

Published and Presented Work

A Probabilistic Model for API contract Specification Retrieval focusing on the OpenAPI Standard
Sae Young Moon, Gregor Kerr, Fran Silavong, Sean Moran. In Data Mining and Knowledge Discovery Journal, 2024
[ Code ]

Evaluating and Enhancing Code Quality with GPT Models
Rundong Liu, Andre Frade, Amal Vaidya, Maxime Labonne, Marcus Kaiser, Bismayan Chakrabarti, Sean Moran. In Arxiv, 2024.

An Unsupervised Method for Estimating Class Separability of Datasets with Application to LLMs Fine-Tuning
Najah Ghalyan, Kostis Gourgoulias, Yash Satsangi, Sean Moran, Maxime Labonne, Joseph Sabelja. In TMLR, 2024.

Model-Agnostic Utility-Preserving Biometric Information Anonymization
Bill Moriarty, Chun-Fu Chen, Shaohan Hu, Sean Moran, Marco Pistoia, Vincenzo Piuri, Pierangela Samarati. In International Journal of Information Security, 2024.

DeepClean: Machine Unlearning on the Cheap by Resetting Privacy Sensitive Weights using the Fisher Diagonal
Jialei Shi, Najah Ghalyan, Kostis Gourgoulias, John Buford, Sean Moran. In Unlearning and Model Editing Workshop @ ECCV, 2024.
[ Slides ]

Using AI/ML to Find and Remediate Enterprise Secrets in Code & Document Sharing Platforms
Gregor Kerr, David Algorry, Senad Ibraimoski, Peter Maciver, Sean Moran. In Arxiv, 2023.

Spam-T5: Benchmarking Large Language Models for Few-Shot Email Spam Detection
Maxime Labonne, Sean Moran. In International Symposium on Large Language Models for Financial Services (FinLLM 2023)@IJCAI, 2023.
[ code ]

A Benchmark Generative Probabilistic Model for Weak Supervised Learning
Georgios Papadopoulos, Fran Silavong, Sean Moran. In ECML PKDD, 2023.

Learning a Consensus Sub-Network with Polarization Regularization and One Pass Training
Xiaoying Zhi, Varun Babbar, Pheobe Sun, Fran Silavong, Ruibo Shi, Sean Moran. In Arxiv, 2022.

API-Miner: an API-to-API Specification Recommendation Engine
Sae Young Moon, Gregor Kerr, Fran Silavong, Sean Moran. In The 1st Workshop on Software Engineering Challenges in Financial Firms (FinanSE), 2024
[ Code ]

Towards Data Efficient and Robust Speech Representation Model Distillation
Pheobe Sun, Ruibo Shi, Ahmad Emami, Sean Moran. In NeurIPS ENLSP Workshop, 2022.

Code Librarian: A Software Package Recommendation Engine
Lili Tao, Alexandru-Petre Cazan, Senad Ibraimoski and Sean Moran. In ICSE SEIP, 2023.

Topical: Learning Repository Embeddings from Source Code using Attention
Agathe Lherondelle, Varun Babbar, Yash Satsangi, Fran Silavong, Shaltiel Eloul, Sean Moran. In The 1st Workshop on Software Engineering Challenges in Financial Firms (FinanSE), 2024.

Ledgit: A Service to Diagnose Illicit Addresses on Blockchain using Multi-Modal Unsupervised Learning
Xiaoying Zhi, Yash Satsangi, Sean Moran, Shaltiel Eloul. In CIKM, 2022.
[ poster ][ bibtex ]

Utility Preserving Biometric Information Anonymization
Bill Moriarty, Chun-Fu Chen, Shaohan Hu, Sean Moran, Marco Pistoia, Vincenzo. Piuri, Pierangela Samarati, In ESORICS, 2022.

CV4Code: Sourcecode Understanding via Visual Code Representations
Ruibo Shi, Lili Tao, Rohan Saphal, Fran Silavong, and Sean Moran. In ACCV, 2022.
[ poster ][ bibtex ] [ code ]

Enhancing Privacy against Inversion Attacks in Federated Learning by using Mixing Gradients Strategies
Shaltiel Eloul, Fran Silavong, Sanket Kamthe, Antonios Georgiadis, Sean Moran. In WACV, 2024.
talk ] [ poster ]

Senatus: A Fast and Accurate Code-To-Code Recommendation Engine
Fran Silavong, Sean Moran, Antonios Georgiadis, Rohan Saphal, Robert Otter. In Mining Software Repositories (MSR) Conference, 2022.
[ bibtex ]

ST-FL: style transfer preprocessing in federated learning for COVID-19 segmentation.
Antonios Georgiadis, Varun Babbar, Fran Silavong, Sean Moran, Robert Otter. In SPIE Medical Imaging, 2022.
[ poster ]

Improving Streaming Cryptocurrency Transaction Classification via Biased Sampling and Graph Feedback.
Shaltiel Eloul, Sean Moran, Jacob Mendel. In ACSAC, 2021.

Low light video Enhancement using Synthetic Data Produced with an Intermediate Domain Mapping.
Danai Triantafyllidou,Sean Moran, Steven McDonagh, Sarah Parisot, Gregory Slabaugh. In ECCV, 2020.
[ bibtex ] [ code ] [ supplementary ] [ 10 minute video ] [ 1 minute video ]

DeepLPF: Deep Local Parametric Filters For Image Enhancement.
Sean Moran, Pierre Marza, Steven McDonagh, Sarah Parisot, Gregory Slabaugh. In CVPR, 2020.
[ bibtex ] [ code ] [ supplementary ] [ poster ] [ slides ] [ 1 minute video ]

CURL: Neural Curve Layers for Global Image Enhancement.
Sean Moran, Steven McDonagh, Gregory Slabaugh. In ICPR, 2020.
[ bibtex ] [ talk (ICPR) ] [ talk (IADS) ] [ poster ] [ code ] [ video ] [ supplementary ]

NODE: Extreme Low Light Raw Image Denoising using a Noise Decomposition Network.
Hao Guan, Liu Liu, Sean Moran, Fenglong Song, Gregory Slabaugh. In Arxiv, 2019.
[ bibtex ]

A Novel Genomics-Based Platform for the Creation of Environmental-Responsive Gene Promoters.
Juan Manuel Iglesias, Ross M. Fraser, Sean Moran, Patricia del Rio, Katie Baker, Sinclair Cooper, Graham Whyteside, Nicolle Kippen, Polyxeni Katsoupi, Rinku Rajan, Jorge Yanez, Michael L. Roberts. In Molecular Therapy 2018.
[ Abstract ]

Learning to Hash for Computer Vision and Image Retrieval
Sean Moran. In Arxiv 2019.

Learning to Project and Binarise for Hashing Based Approximate Nearest Neighbour Search.
Sean Moran. In SIGIR, 2016.
[ bibtex ] [ poster ]

Enhancing First Story Detection using Word Embeddings.
Sean Moran, Richard McCreadie, Craig MacDonald, Iadh Ounis. In SIGIR, 2016.
[ bibtex ]

Learning to Hash for Large-Scale Image Retrieval.
Sean Moran (PhD thesis, 2015)
[ bibtex ]

Regularised Cross-Modal Hashing.
Sean Moran, Victor Lavrenko. In SIGIR, 2015.
[ bibtex ] [ poster ] [ code ] [ datasets ]

A Note on Automatic Kernel Carpentry for Atomistic Support of Continuum Stress
Manfred Ulz, Sean Moran. In Arxiv, 2015.
[ bibtex ]

Graph Regularised Hashing.
Sean Moran, Victor Lavrenko. In ECIR, 2015.
[ bibtex ] [ talk ] [ poster ] [ code ] [ datasets ]

A Sparse Kernel Relevance Model for Automatic Image Annotation.
Sean Moran, Victor Lavrenko. In IJMIR 2014 (Best Papers in Image Retrieval).
[ bibtex ] [ code ] [ datasets ]

Sparse Kernel Learning for Image Annotation.
Sean Moran, Victor Lavrenko. In ICMR 2014 (Oral) (Best Student Paper Winner).
[ bibtex ] [ talk ] [ code ] [ datasets ]

Real-Time Detection, Tracking and Monitoring of Discovered Events in Social Media.
Sean Moran et al. In ACL 2014 (Demo).
[ bibtex ]

Optimal Kernel Shape and Bandwidth for Atomistic Support of Continuum Stress.
Manfred Ulz, Sean Moran. In MSMSE 2013.
[ bibtex ]

Variable Bit Quantisation for LSH.
Sean Moran, Victor Lavrenko, Miles Osborne. In ACL 2013.
[ bibtex ] [ talk ][ code ] [ datasets ]

Neighbourhood Preserving Quantisation for LSH.
Sean Moran, Victor Lavrenko, Miles Osborne. In SIGIR 2013.
[ bibtex ] [ poster ] [ code ] [ datasets ]

A Gaussian mixture modelling approach to the data-driven estimation of atomistic support for continuum stress.
Manfred Ulz, Sean Moran. In MSMSE 2012.
[ bibtex ]

Optimal Tag Sets for Automatic Image Annotation.
Sean Moran, Victor Lavrenko. In BMVC 2011.
[ bibtex ] [ abstract ] [ talk ]

Linking Video Segments to Relevant Wikipedia Content
Victor Larevnko, Johanna Moore, Sean Moran (2010).

Automatic Image Tagging.
Sean Moran (MSc Disseration, 2009).

Video Inpainting (Overview)
Sean Moran (2009).

Using the Grid for Satellite Imagery with UNOSAT.
Sean Moran, Patricia Mendez Lorenzo. Internal UNOSAT-CERN report, 2005

Robust Fusion of Colour Appearance Models for Object Tracking.
Chris Town, Sean Moran. In BMVC 2004.
[ bibtex ]