Assistant Professor at Institute of Science Tokyo since October 2024.

My main research focus is on bridging the gap between symbolic AI and neural networks.

During my Ph.D., I developed deep learning techniques that extract symbolic rules from time series data. These rules explain the observed data and can be used to predict and manipulate dynamic systems — a step toward explainable AI systems that provide human-accessible insights into complex behaviour.

I am now developing techniques that combine the strengths of both worlds. Symbolic AI produces knowledge that is directly readable by humans, but is brittle and hard to scale; neural networks are robust and broadly applicable, but the knowledge they encode is hard to access. By combining both approaches I aim to build intelligent systems that are simultaneously robust enough for real-world deployment and transparent enough to teach us something. Most recently, this led to the Neural Rule Inducer (NRI), a foundation model that induces human-readable logical rules on new datasets in a single forward pass, accepted to IJCAI 2026.

Research areas: neuro-symbolic AI, foundation models, logical rule induction, inductive logic programming (ILP), deep learning, explainable AI (XAI), time series analysis, and robustness.

Have interesting projects or want to have some discussion? You can contact me at phua [at] comp.isct.ac.jp

Goal

Neural networks now drive most of AI, but the knowledge they acquire remains impenetrable to the people who rely on them. My long-term goal is to make that knowledge readable, auditable, and correctable — so that a doctor, an engineer, or a scientist can see what a model has learned, challenge it, and build on it. Toward this, I am developing foundation models that learn generalizable, interpretable knowledge from background knowledge and limited data, and logical reasoning techniques that make generative AI reliable.

Selected Publications

A Foundation Model for Zero-Shot Logical Rule Induction [arXiv]
Yin Jun Phua
35th International Joint Conference on Artificial Intelligence (IJCAI), 2026.

Variable Assignment Invariant Neural Networks for Learning Logic Programs
Yin Jun Phua, Katsumi Inoue
18th International Conference on Neural-Symbolic Learning and Reasoning (NeSy), 2024.

Class-Incremental Learning using Diffusion Model for Distillation and Replay [Best Paper Award]
Quentin Jodelet, Xin Liu, Yin Jun Phua, Tsuyoshi Murata
1st Workshop on Visual Continual Learning, ICCV 2023.

resVAE ensemble: Unsupervised identification of gene sets in multi-modal single-cell sequencing data using deep ensembles
Foo Wei Ten, Dong Sheng Yuan, Nabil Jabareen, Yin Jun Phua, Richard Eils, Soeren Lukassen, Christian Conrad
Frontiers in Cell and Developmental Biology, 11, 2023.

Learning Logic Programs Using Neural Networks by Exploiting Symbolic Invariance
Yin Jun Phua, Katsumi Inoue
30th International Conference on Inductive Logic Programming (ILP), 2021.

Learning Logic Programs from Noisy State Transition Data [Best Student Paper Award]
Yin Jun Phua, Katsumi Inoue
29th International Conference on Inductive Logic Programming (ILP), 2019.

Full publication list on dblp »

Research Projects/Grants

Developing AI Systems through Data-driven Learning of Generalized Interpretable Knowledge from Background Knowledge and Limited Data
Principal Investigator ￥ 4,680,000
Grant-in-Aid for Early-Career Scientists,
Japan Society for the Promotion of Science
April 2025 - March 2028

Constraint Reasoning for Trustworthy AI
Co-Investigator ￥ 18,720,000
Grant-in-Aid for Scientific Research (B),
Japan Society for the Promotion of Science
April 2025 - March 2029

Towards Reliable Generative AI by Separated Search State Control Mechanism
Principal Investigator ￥ 1,120,000
Open Collaborative Research,
National Institute of Informatics
July 2026 - March 2027

Discovering New Knowledge by Combining Symbolic Logic and Deep Learning
Principal Investigator ￥ 2,860,000
Grants-in-Aid for Scientific Research Grant-in-Aid for Research Activity Start-up,
Japan Society for the Promotion of Science
August 2022 - March 2024

Towards Reliable Generative AI by Logical Reasoning
Principal Investigator ￥ 975,000
Open Collaborative Research,
National Institute of Informatics
July 2024 - March 2025

Research on Intelligence and Consciousness
Principal Investigator ￥ 950,000
New Research Challenge Incentive Fund,
Organization for Fundamental Research, Tokyo Institute of Technology
September 2023 - March 2025

Robust AI by Integration of Knowledge Representation and Machine Learning
Co-Investigator ￥ 41,470,000
Grant-in-Aid for Scientific Research (A),
Japan Society for the Promotion of Science
April 2022 - March 2025

Understandable Model by Combination of Symbolic Machine Learning and Deep Statistical Learning
Research Fellow ￥ 1,500,000
Grants-in-Aid for Scientific Research Grant-in-Aid for JSPS Fellows,
Japan Society for the Promotion of Science
April 2021 - March 2022