publications

Publications, patents, technical reports, thesis, and conference papers.

I am a named inventor on granted patents covering perception uncertainty, perception error modelling, and simulation-based testing (Espacenet).

Papers:

2026

  1. CaliBench: Are the Stochastic Dynamics of Video World Models Physically Calibrated?
    Jonathan Sadeghi, Jenny Seidenschwarz, Jesse Allardice, Sirish Srinivasan, Benjamin Graham, and Jeffrey Hawke
    Transactions on Machine Learning Research (TMLR), 2026
    arXiv Code
  2. PROWL: Prioritized Regret-Driven Optimization for World Model Learning
    Ahmet H. Güzel, Jenny Seidenschwarz, Benjamin Graham, Jonathan Sadeghi, Jeffrey Hawke, Jack Parker-Holder, and Ilia Bogunovic
    2026
    arXiv Website

2024

  1. On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines
    Selim Kuzucu, Kemal Oksuz, Jonathan Sadeghi, and Puneet K. Dokania
    ECCV, 2024
    arXiv Code

2023

  1. Attacking Motion Planners Using Adversarial Perception Errors
    Jonathan Sadeghi, Nicholas A. Lord, John Redford, and Romain Mueller
    2023
    DOI arXiv

2022

  1. An Active Learning Reliability Method for Systems with Partially Defined Performance Functions
    Jonathan Sadeghi, Romain Mueller, and John Redford
    NeurIPS 2022 Workshop on Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems (GPSMDMS), 2022
    DOI arXiv Video Code
  2. Query-based Hard-Image Retrieval for Object Detection at Test Time
    Edward Ayers, Jonathan Sadeghi, John Redford, Romain Mueller, and Puneet K. Dokania
    Thirty-Seventh AAAI Conference on Artificial Intelligence, 2022
    DOI arXiv Code
  3. Perspectives on the System-level Design of a Safe Autonomous Driving Stack
    Majd Hawasly, Jonathan Sadeghi, Morris Antonello, Stefano V. Albrecht, John Redford, and Subramanian Ramamoorthy
    AI Communications, 2022
    DOI arXiv

2021

  1. A Step Towards Efficient Evaluation of Complex Perception Tasks in Simulation
    Jonathan Sadeghi, Blaine Rogers, James Gunn, Thomas Saunders, Sina Samangooei, Puneet Kumar Dokania, and John Redford
    NeurIPS 2021 Workshop on Machine Learning for Autonomous Driving (ML4AD), 2021
    arXiv Video

2019

  1. Robust propagation of probability boxes by Interval Predictor Models
    Jonathan Sadeghi, Marco de Angelis, and Edoardo Patelli
    Structural Safety, 2019
    DOI
  2. Efficient Training of Interval Neural Networks for Imprecise Training Data
    Jonathan Sadeghi, Marco de Angelis, and Edoardo Patelli
    Neural Networks, 2019
    PDF Code
  3. Analytic Probabilistic Safety Analysis Under Severe Uncertainty
    Jonathan Sadeghi, Marco de Angelis, and Edoardo Patelli
    ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering, 2019
    DOI
  4. On the robust estimation of small failure probabilities for strong non-linear models
    Matthias Faes, Jonathan Sadeghi, Matteo Broggi, Marco de Angelis, Edoardo Patelli, Michael Beer, and David Moens
    ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part B: Mechanical Engineering, 2019
    DOI

2016

  1. Structural reliability of pre-stressed concrete containments
    Nawal K. Prinja, Azeezat Ogunbadejo, Jonathan Sadeghi, and Edoardo Patelli
    Nuclear Engineering and Design, Dec 2016
    DOI

Thesis:

2020

  1. Uncertainty Modelling for Scarce and Imprecise Data in Engineering Applications
    Jonathan Sadeghi
    University of Liverpool, 2020
    Website

Technical Reports:

2026

  1. Odyssey-2 Max: Scaled World Simulation
    Ahmad Nazeri, Ahmet Hamdi Guzel, Alexandra Chan, Amogh Adishesha, Andrew Trout, Andy Kolkhorst, Aravind Kaimal, Ben Graham, Derek Sarshad, Fabian Güra, Finley Code, James Grieve, Jeff Hawke, Jenny Seidenschwarz, Jesse Allardice, Jessica Inman, Jonathan Sadeghi, Kaiwen Guo, Kristy McDonough, Nicolas Griffiths, Nima Rezaeian, Oliver Cameron, Renee Huang, Richard Shen, Robin Tweedie, Sarah King, Sirish Srinivasan, Tobiah Rex, Vighnesh Birodkar, Vinh-Dieu Lam, and Zygmunt Łenyk
    2026
    Website

2019

  1. Data Study Group Final Report: Global bank
    Data Study Group team
    Alan Turing Institute, Feb 2019
    DOI

Conference Papers/Talks:

2018

  1. Robust propagation of probability boxes by Interval Predictor Models
    Jonathan Sadeghi, Marco de Angelis, and Edoardo Patelli
    In Proceedings of the joint ASCE ICVRAM ISUMA UNCERTAINTIES conference, 2018
  2. OpenCossan 2.0: an efficient computational toolbox for risk, reliability and resilience analysis
    Edoardo Patelli, Silvia Tolo, Hindolo George-Williams, Jonathan Sadeghi, Roberto Rocchetta, Marco de Angelis, and Matteo Broggi
    In Proceedings of the joint ASCE ICVRAM ISUMA UNCERTAINTIES conference, 2018
    Website
  3. Probability Box Propagation: Benchmarking Challenge Problems
    Edoardo Patelli, Jonathan Sadeghi, Marco de Angelis, Thomas Fetz, and Micheal Oberguggenberger
    In 19th working conference of the IFIP Working Group 7.5 on Reliability and Optimization of Structural Systems, 2018

2017

  1. Cossan Software: A Multidisciplinary And Collaborative Software For Uncertainty Quantification
    Edoardo Patelli, Matteo Broggi, Silvia Tolo, and Jonathan Sadeghi
    In 2nd ECCOMAS Thematic Conference on Uncertainty Quantification in Computational Sciences and Engineering, 2017
    DOI