Adam R. Kosiorek

Hi, I’m Adam. I’m passionate about machine learning, particularly machine reasoning and generative modelling. I’m really into time-series, attention, external memory and VAEs.

Along my studies, I worked at Bloomberg, Samsung and IBM on various machine learning projects. I am always looking for exciting research and professional opportunities, so feel free to get in touch

In my free time I read lots of books, train gymnastics, lift heavy weights and hike mountains.

My CV (updated 10/2018)


J. Lee, Y. Lee, J. Kim, A. R. Kosiorek, S. Choi, Y. W. Teh “Set Transformer”, CoRR, 2018.

A. R. Kosiorek, H. Kim, I. Posner, Y. W. Teh “Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects”, NIPS, 2018.

T. A. Le, A. R. Kosiorek, N. Siddharth, Y. W. Teh, F. Wood “Revisiting Reweighted Wake-Sleep”, CoRR, 2018.

F. B. Fuchs, O. Groth, A. R. Kosiorek, A. Bewley, M. Wulfmeier, A. Vedaldi, I. Posner “Neural Stethoscopes: Unifying Analytic, Auxiliary and Adversarial Network Probing”, CoRR, 2018.

T. Rainforth, A. R. Kosiorek, T. A. Le, C. J. Maddison, M. Igl, F. Wood, Y. W. Teh, “Tighter Variational Bounds are Not Necessarily Better”, CoRR, 2018.

A. R. Kosiorek, A. Bewley, I. Posner, “Hierarchical Attentive Recurrent Tracking”, NIPS, 2017. code

N. Dhir, A. R. Kosiorek, I. Posner, “Bayesian Delay Embeddings for Dynamical Systems”, NIPS Timeseries Workshop, 2017.

Equal contribution.


An implementation of “Attend, Infer, Repeat” by Ali Eslami et. al. code