Hi! I’m Roman Bachmann, an EPFL PhD student at VILAB, where I’m advised by Amir Zamir. My current research is focused on learning good priors for efficient visual transfer learning. I am also interested in world models, spatial memory, as well as novel view synthesis. My goal is to build adaptable world priors that enable quick understanding of the environment and allow for global, out-of-sight reasoning.

I received my M.Sc. degree in Data Science at EPFL, where I also previously completed my B.Sc. in Computer Science. During my Master, I also worked as a research intern in the Approximate Bayesian Inference Team under the supervision of Emtiyaz Khan at RIKEN AIP.



Roman Bachmann*, David Mizrahi*, Andrei Atanov, Amir Zamir

2022 European Conference on Computer Vision

Yael Vinker, Ehsan Pajouheshgar, Jessica Y. Bo, Roman Bachmann, Amit Haim Bermano, Daniel Cohen-Or, Amir Zamir, Ariel Shamir


Selected as one of the five Best Paper Award winners


Ainaz Eftekhar*, Alexander Sax*, Roman Bachmann, Jitendra Malik, Amir Zamir

2021 International Conference on Computer Vision


Xiangming Meng, Roman Bachmann, and Mohammad Emtiyaz Khan

2020 International Conference on Machine Learning


Roman Bachmann, Jörg Spörri, Pascal Fua, and Helge Rhodin

2019 International Conference on 3D Vision

Selected for oral presentation

Roman Bachmann, Helge Rhodin, and Pascal Fua

2019 Central European Seminar on Computer Graphics (non-peer-reviewed)

Voted best presentation and third best paper

Roman Bachmann, Helge Rhodin, Jörg Spörri, and Pascal Fua

8th Int. Congress on Science and Skiing (non-peer-reviewed)

Won first place in the Young Investigator Award competition