Compressing Prime Numbers: Kolmogorov Complexity 101
A tiny bit of light on Kolmogorov Complexity and the incompressibility method.
Welcome to my humble abode! I am a Junior Research Fellow (JRF) in Computer Science at Trinity College, Oxford. Besides my role at Trinity, I also hold research positions at the University of Oxford (Associate Research Fellow) and the University of Cambridge (Affiliated Lecturer and Visiting Researcher). I am also a member of the European Laboratory for Learning and Intelligent Systems (ELLIS), and a co-organizer of the Interpretable Deep Learning Seminar Series (feel free to reach out if you would like to present your work in this series!).
My research lies within the general field of Artificial Intelligence (AI), where I am roughly interested in research areas related to AI Safety. Specifically, I am interested in the intersection of interpretability (e.g., explaining a model using human-like concepts), representation engineering and learning (e.g., how can one manipulate representations to influence, control, or steer model behavior), and human-AI collaboration (e.g., test-time feedback and interventions). To find out more about my research, please see my research page.
If you would like to collaborate or chat, feel free to send me an email. I am always happy to connect and to discuss potential collaborations, supervisions, or research ideas!
Featured Publications
-
ICML 2025
Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
We show how, under distribution shifts, concept-based interventions may fail to improve model performance due to concept leakage. To solve this, we introduce a representation factorisation that prevents this effect, leading to more robust and reliable concept-based models.
-
ECCV 2024 · Oral, Best Paper Candidate
Efficient Bias Mitigation Without Privileged Information
We argue that existing unsupervised debiasing methods still implicitly rely on group information for model selection. To solve this, we introduce an efficient hyperparameter-free bias mitigation approach called TAB.
-
NeurIPS 2022
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off
We introduce a new concept-based interpretable neural network that remains interpretable and intervenable even when the concept supervision is incomplete.
Recent News
-
Persistent SAEs paper accepted at the NeurIPS workshop on Interpretability as a Science.
-
Our paper on steering (led by the amazing Haoyan Luo) was accepted at NeurIPS 2026 🇦🇺 as a spotlight (top ~1% of submissions)!
-
Lucky to have three accepted papers [1, 2, 3], including one spotlight paper, at ICML 2026 🇰🇷!
-
Gave an invited talk at ICLR 2026's Unifying Concept Representation Learning Workshop!
-
We started a new seminar series on interpretable AI. Everyone is more than welcome to join!
-
Co-presented a tutorial on Foundations of Interpretable Deep Learning at AAAI 2026 🇸🇬.
-
Our paper on hierarchical concept discovery was accepted at ICLR 2026 🇧🇷!
-
Passed my PhD defense (viva voce) without corrections.
-
Started a Junior Research Fellowship (JRF) in Computer Science at Trinity College, Oxford.
-
Pietro Barbiero and I gave a talk on Foundations of Interpretable Models at the Neuro-Symbolic AI Summer School based on this paper.
-
Co-presented a tutorial on Concept-based Interpretable Deep Learning at AAAI 2025 🇺🇸.
Earlier highlights
-
Our Causal Concept Graph Models work was accepted at ICLR 2025 🇸🇬.
-
Our work on unsupervised bias mitigation was accepted at ECCV 2024 🇮🇹 as an oral and nominated for Best Paper.
-
One paper was accepted at ICML 2024 🇦🇹 where I also co-organized the LatinX in AI workshop.
-
Our IntCEM paper was accepted at NeurIPS 2023 🇺🇸 as a spotlight.
-
Our Concept Embedding Model paper was accepted at NeurIPS 2022 🇺🇸.
-
Completed my MEng in Computer Science at Cornell University with the highest GPA in my cohort.
Recent Posts
On Bizarre Mathematics
Welcome to my blog! Here is something weird for you…