Roman Bachmann

Hi! I'm Roman Bachmann, a Machine Learning Research Scientist at Apple. My research is focused on building scalable any-to-any multimodal foundation models for world modelling and visual reasoning. My goal is to build adaptable world priors that enable quick understanding of the environment and allow for global, out-of-sight reasoning.

Previously I was an EPFL PhD student at VILAB, advised by Amir Zamir. I received my M.Sc. degree in Data Science at EPFL, where I also completed my B.Sc. in Computer Science. During my studies, I interned as a research scientist at Apple and RIKEN AIP.

Highlighted publications

FlexTok: Resampling Images into 1D Token Sequences of Flexible Length →

Roman Bachmann*, Jesse Allardice*, David Mizrahi*, Enrico Fini, Oğuzhan Fatih Kar, Elmira Amirloo, Alaaeldin El-Nouby, Amir Zamir, Afshin Dehghan

ICML 2025

arXiv Website Code

FlexTok: Resampling Images into 1D Token Sequences of Flexible Length

4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities →

Roman Bachmann*, Oğuzhan Fatih Kar*, David Mizrahi*, Ali Garjani, Mingfei Gao, David Griffiths, Jiaming Hu, Afshin Dehghan, Amir Zamir

NeurIPS 2024

★ >1.8k stars on GitHub

arXiv Website Code

4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities

4M: Massively Multimodal Masked Modeling →

David Mizrahi*, Roman Bachmann*, Oğuzhan Fatih Kar, Teresa Yeo, Mingfei Gao, Afshin Dehghan, Amir Zamir

NeurIPS 2023

★ Spotlight

arXiv Website Code

4M: Massively Multimodal Masked Modeling

MultiMAE: Multi-modal Multi-task Masked Autoencoders →

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

ECCV 2022

arXiv Website Code

MultiMAE: Multi-modal Multi-task Masked Autoencoders

All publications

2026

MintAct: A Unified Visual Agent for Digital Environments →

Mingfei Gao, Rui Tian, Haiming Gang, Bohan Zhai, Le Zhang, Yuanzheng Gong, Di Feng, Ege Özsoy, Kaixin Ma, Vishwesh Kirthivasan, Oğuzhan Fatih Kar, Roman Bachmann, Anders Boesen Lindbo Larsen, Afshin Dehghan

Under review

arXiv

MintAct: A Unified Visual Agent for Digital Environments

Weblica: Scalable and Reproducible Training Environments for Visual Web Agents →

Oğuzhan Fatih Kar, Roman Bachmann, Yuanzheng Gong, Anders Boesen Lindbo Larsen, Afshin Dehghan

Under review

arXiv

Weblica: Scalable and Reproducible Training Environments for Visual Web Agents

OmniDiMM: Bridging 1D, 2D, and 3D with Any-to-Any Multimodal Modeling →

Jason Toskov*, Oriol Barbany*, Rishubh Singh*, Jinya Sakurai, Efe Tarhan, Oğuzhan Fatih Kar, Roman Bachmann, Amir Zadeh, Jesse Allardice, Chuan Li, Carme Torras, Afshin Dehghan, Amir Zamir

NeurIPS 2026

Website

Any-to-Any Video Modeling: Modeling the World by Traversing Time and Modalities →

Muhammad Uzair Khattak, Won Jun Kim, Reza Abbasi, Albias Havolli, Michael Murphy, Amir Zadeh, Chuan Li, Muhammad Ferjad Naeem, Oğuzhan Fatih Kar, Roman Bachmann, Andrei Atanov, Federico Tombari, Amir Zamir

Under review

PDF Website

MODUS: Decoder-only Any-to-Any Modeling of Diverse Modalities →

Mingqiao Ye*, Zhaochong An*, Zhitong Gao, Xian Liu, François Fleuret, Chuan Li, Amir Zadeh, Serge Belongie, Afshin Dehghan, Jesse Allardice†, David Mizrahi†, Oğuzhan Fatih Kar†, Roman Bachmann†, Amir Zamir

ICML 2026

arXiv Website Code Dataset

MODUS: Decoder-only Any-to-Any Modeling of Diverse Modalities

(1D) Ordered Tokens Enable Efficient Test-Time Search →

Zhitong Gao, Parham Rezaei, Ali Cy, Mingqiao Ye, Nataša Jovanović, Jesse Allardice, Afshin Dehghan, Amir Zamir, Roman Bachmann†, Oğuzhan Fatih Kar†

ICML 2026

arXiv Website Code