I am a PhD Computer Science Student (started April 2022) at the Computational Logic and Argumentation group at Department of Computing, Imperial College London, supervised by Professor Francesca Toni, working with Dr Francesco Leofante and Dr Antonio Rago. My PhD is funded by the Interactive Explainable AI project. I’m a teaching assistant during PhD. I also supervise thesis for undergraduate and taught postgraduate students.

From June to December 2024, I interned as an AI Research Associate at J.P. Morgan Explainable AI Center of Excellence, working with Dr Tom Bewley and Dr Saumitra Mishra.

Previously, I completed an MSc Computer Science degree from Imperial. I hold two BEng Electrical Engineering degrees from The University of Edinburgh and South China University of Technology.

Research

My research interest lies in the broad field of AI trustworthiness. I have focused on robust explainable AI - specifically robust counterfactual explanations for recourse purposes, and topics in model multiplicity - when there are multiple competing machine learning models potentially giving conflicting predictions, also known as predictive multiplicity. I have worked on these topics in both traditional machine learning for tabular data and modern large language models (LLM) for textual data.

I’m also interested in the application of explainablility, and have contributed to applied machine learning projects for city planning and Formula One race strategy.

So far, my research works have been published at top venues like ICLR, AAAI, IJCAI, AAMAS, KR conferences, and Artificial Intelligence, Information Fusion journals. Below is the list of all my publications. Please also refer to my Google Scholar page.

Feel free to get in touch via email or LinkedIn!

2025

🎷 Interpreting Language Reward Models via Contrastive Explanations
[ICLR 2025] The 13th International Conference on Learning Representations
J. Jiang, T. Bewley, S. Mishra, F. Lecue, M. Veloso

🎷 RobustX: Robust Counterfactual Explanations Made Easy
[Preprint 2025]
J. Jiang, L. Marzari, A. Purohit, F. Leofante

Heterogeneous Graph Neural Networks with Post-hoc Explanations for Multi-modal and Explainable Land Use Inference
[Inf. Fusion 2025] Information Fusion
X. Zhai, J. Jiang, A. Dejl, A. Rago, F. Guo, F. Toni, A. Sivakumar

Explainable Reinforcement Learning for Formula One Race Strategy
[SAC 2025] The 40th ACM/SIGAPP Symposium on Applied Computing
D. Thomas, J. Jiang, A. Kori, A. Russo, S. Winkler, S. Sale, J. McMillan, F. Belardinelli, A. Rago

Explainable Time Series Prediction of Tyre Energy in Formula One Race Strategy
[SAC 2025] The 40th ACM/SIGAPP Symposium on Applied Computing
J. Todd, J. Jiang, A. Russo, S. Winkler, S. Sale, J. McMillan, A. Rago

2024

🎷 Interval Abstractions for Robust Counterfactual Explanations
[AIJ 2024] Artificial Intelligence
J. Jiang, F. Leofante, A. Rago, F. Toni

🎷 Robust Counterfactual Explanations in Machine Learning: A Survey
[IJCAI 2024] The 33rd International Joint Conference on Artificial Intelligence, Survey Track
J. Jiang, F. Leofante, A. Rago, F. Toni

🎷 Recourse under Model Multiplicity via Argumentative Ensembling
[AAMAS 2024] The 23rd International Conference on Autonomous Agents and Multi-Agent Systems
J. Jiang, F. Leofante, A. Rago, F. Toni
Nominated for Best Student Paper Award at AAMAS 2024, runner-up

Contestable AI needs Computational Argumentation
[KR 2024] The 21st International Conference on Principles of Knowledge Representation and Reasoning
F. Leofante, H. Ayoobi, A. Dejl, G. Freedman, D. Gorur, J. Jiang, G. Paulino-Passos, A. Rago, A. Rapberger, F. Russo, X. Yin, D. Zhang, F. Toni

2023

🎷 Formalising the Robustness of Counterfactual Explanations for Neural Networks
[AAAI 2023] The 37th AAAI Conference on Artificial Intelligence
J. Jiang*, F. Leofante*, A. Rago, F. Toni

🎷 Provably Robust and Plausible Counterfactual Explanations for Neural Networks via Robust Optimisation
[ACML 2023] The 15th Asian Conference on Machine Learning
J. Jiang, J. Lan, F. Leofante, A. Rago, F. Toni

_{* equal contributions
🎷 publications where I’m the lead author. Using this emoji because I’m a saxophonist :)}