Kianoosh Ashouritaklimi
I’m a third year DPhil student in the Department of Statistics at the University of Oxford, supervised by Tom Rainforth and François Caron. Broadly speaking, I am interested in developing reliable statistical methods for label-efficient testing and monitoring of machine learning models. Previously, I have worked on conformal prediction [1, 2], active testing/learning [3, 4], and generative modeling [5, 6, 7].
Before starting my PhD, I completed my MSc in Artificial Intelligence at Imperial College London where I was awarded a Google DeepMind Scholarship. For my dissertation, I analyzed the quality of Bayesian neural network approximations under the supervision of Mark van der Wilk.
I am also passionate about social mobility and widening participation in higher education. Previously, I was an EDI fellow at the University of Oxford, where I had the opportunity to work on the university’s postgraduate recruitment campaigns and initiatives.
Feel free to reach out to me via email or connect with me on LinkedIn!
News
| Sep 25, 2026 | Our paper “Prediction-Powered Active Testing” has been accepted to NeurIPS 2026! Check out the arXiV preprint. |
|---|---|
| Jun 01, 2026 | Check out our new work “Masked Language Flow Models” on arXiV. |
| May 01, 2026 | Our paper “Variance-Tilted Diffusion Models for Diverse Sampling” was accepted at the Structured Probabilistic Inference and Generative Modeling Workshop at ICML 2026. |
| May 01, 2026 | Our paper “Prediction-Powered Active Testing” was accepted at the Statistical Frameworks for Uncertainty in Agentic Systems Workshop at ICML 2026. Full preprint available on arXiV. |
| Mar 01, 2026 | Our paper “Conformal Calibration from Unlabelled Pools” was accepted at the Towards Trustworthy Predictions: Theory and Applications of Calibration for Modern AI Workshop at AISTATS 2026. |
| Feb 01, 2026 | Our paper “Robust Bayes-Assisted Conformal Prediction” was accepted at ICML 2026. |
| Sep 01, 2025 | Our preprint “Active Learning with Task-Driven Representations for Messy Pools” is now available on arXiv. |
| Sep 01, 2024 | Our paper “SymDiff: Equivariant Diffusion via Stochastic Symmetrisation” was accepted at ICLR 2025. |
| Sep 01, 2023 | I started my DPhil at the University of Oxford. |