Yee Whye Teh
Professor of Statistical Machine Learning at the University of Oxford & Research Director at Google DeepMind
AI Visiting Professor at NTU and NUS
IAS SEMINAR #14/2026
Turin / OGR / Mezzanino / September 03, 2026 / 04:00 – 06:00 pm CEST
Diffusion and flow-based models for inverse problems
EVENT&WEBINAR
Across diverse scientific domains, scientists face the same fundamental problem: they must infer unknown images or physical states from incomplete, noisy, or indirect measurements/constraints. In such inverse problems, measurements alone are insufficient to determine a unique answer, so reliable inference must draw on prior scientific knowledge about realistic solutions and report calibrated uncertainties over multiple solutions consistent with both prior knowledge and measurements. This can be framed as Bayesian inference, where generative AI methods based on diffusions and flows represent complex scientific priors, and steering based methods aim to direct the generative process towards parts of the state space that are consistent with measurements. In this talk I will present two pieces of works in this vein: meta flow-maps (arxiv:2601.14430) use stochastic flow maps to construct high quality steering signals thus improve the performance of reconstructions. Exact posterior scores (arxiv:2606.17048) shows that for linear Gaussian measurements the exact steering signal can be derived and learnt via finetuning to produce state-of-the-art inverse problem solvers. These works are lead by students Peter Potaptchik, Adhi Saravanan and Abbas Mammadov.
YEE WHYE TEH
Prof Teh is a Professor of Statistical Machine Learning at the Department of Statistics, University of Oxford and a Research Director at DeepMind working on AI research. He is also an AI Visiting Professor in Singapore starting this year, visiting NTU and NUS. Prof Teh obtained his Ph.D. at the University of Toronto and did postdoctoral work at the University of California at Berkeley and National University of Singapore (as Lee Kuan Yew Postdoctoral Fellow). He was a Lecturer then a Reader at the Gatsby Computational Neuroscience Unit, UCL from Jan 2007-Aug 2012. Prof Teh’s research interests are in machine learning and artificial intelligence, in particular probabilistic methods, Bayesian non-parametrics and deep learning. He develops novel models as well as efficient algorithms for inference and learning. He gave the Breiman Lecture at NeurIPS 2017, the IMS Medallion Lecture at JSM 2019, and keynotes at MLSP 2017, KDD 2018, UAI 2019.
Register for In-Person Attendance
Joining us in person offers the opportunity for direct networking and interaction with both speakers and participants.
Please complete the form below to reserve your seat.
By clicking, you will be automatically registered for the in-person event.
Note: If you see a message saying you’re already subscribed, please ignore it — your in-person registration will still be confirmed.
Please note that, by attending, you implicitly authorize AI4I to film and photograph the audience during the seminar. By submitting your registration, you acknowledge and accept the AI4I Data Privacy Policy. Seats are limited: if you are unable to attend, we kindly ask you to inform us as soon as possible at ias@ai4i.it
LINK ZOOM
