Oxford Statistics researchers Valentin De Bortoli, Emile Mathieu, Michael Hutchinson, James Thornton, Yee Whye Teh and Arnaud Doucet has received an Outstanding Paper Award at NeurIPS 2022, the key conference in Machine Learning and Artificial Intelligence. Their paper Riemmanian Score-Based Generative Modeling generalizes score-based generative model (SGM) from Euclidean space to Riemannian manifolds by identifying major components that contribute to the success of SGMs. The method is both a novel and technically useful contribution.
This is a fantastic achievement, as only 13 papers out of over 8,000 submissions received such an award. Oxford University
We are delighted to receive an Outstanding Paper Award from NeurIPS. This has numerous exciting applications ranging from protein modelling to robotics which we are actively working on.
Prof Arnaud Doucet