Roman Bachmann

18 papers A* 5Journal 10Unranked 3

Year	Rank	Type	Title / Venue / Authors
2025	A*	`conf`	FlexTok: Resampling Images into 1D Token Sequences of Flexible Length. ICML Roman Bachmann, Jesse Allardice, David Mizrahi, Enrico Fini, Oguzhan Fatih Kar, Elmira Amirloo, Alaaeldin El-Nouby, Amir Zamir, Afshin Dehghan
2025	J	`jnl`	FlexTok: Resampling Images into 1D Token Sequences of Flexible Length. CoRR Roman Bachmann, Jesse Allardice, David Mizrahi, Enrico Fini, Oguzhan Fatih Kar, Elmira Amirloo, Alaaeldin El-Nouby, Amir Zamir, Afshin Dehghan
2025	J	`jnl`	How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks. CoRR Rahul Ramachandran, Ali Garjani, Roman Bachmann, Andrei Atanov, Oguzhan Fatih Kar, Amir Zamir
2024	A*	`conf`	4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities. NeurIPS Roman Bachmann, Oguzhan Fatih Kar, David Mizrahi, Ali Garjani, Mingfei Gao, David Griffiths, Jiaming Hu, Afshin Dehghan, Amir Zamir
2024	J	`jnl`	4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities. CoRR Roman Bachmann, Oguzhan Fatih Kar, David Mizrahi, Ali Garjani, Mingfei Gao, David Griffiths, Jiaming Hu, Afshin Dehghan, Amir Zamir
2024	—	`conf`	ViPer: Visual Personalization of Generative Models via Individual Preference Learning. ECCV (74) Sogand Salehi, Mahdi Shafiei, Teresa Yeo, Roman Bachmann, Amir Zamir
2024	J	`jnl`	ViPer: Visual Personalization of Generative Models via Individual Preference Learning. CoRR Sogand Salehi, Mahdi Shafiei, Teresa Yeo, Roman Bachmann, Amir Zamir
2023	A*	`conf`	4M: Massively Multimodal Masked Modeling. NeurIPS David Mizrahi, Roman Bachmann, Oguzhan Fatih Kar, Teresa Yeo, Mingfei Gao, Afshin Dehghan, Amir Zamir
2023	J	`jnl`	4M: Massively Multimodal Masked Modeling. CoRR David Mizrahi, Roman Bachmann, Oguzhan Fatih Kar, Teresa Yeo, Mingfei Gao, Afshin Dehghan, Amir Zamir
2023	A*	`conf`	Modality-invariant Visual Odometry for Embodied Vision. CVPR Marius Memmel, Roman Bachmann, Amir Zamir
2023	J	`jnl`	Modality-invariant Visual Odometry for Embodied Vision. CoRR Marius Memmel, Roman Bachmann, Amir Zamir
2022	—	`conf`	MultiMAE: Multi-modal Multi-task Masked Autoencoders. ECCV (37) Roman Bachmann, David Mizrahi, Andrei Atanov, Amir Zamir
2022	J	`jnl`	MultiMAE: Multi-modal Multi-task Masked Autoencoders. CoRR Roman Bachmann, David Mizrahi, Andrei Atanov, Amir Zamir
2021	J	`jnl`	Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans. CoRR Ainaz Eftekhar, Alexander Sax, Roman Bachmann, Jitendra Malik, Amir Zamir
2020	A*	`conf`	Training Binary Neural Networks using the Bayesian Learning Rule. ICML Xiangming Meng, Roman Bachmann, Mohammad Emtiyaz Khan
2020	J	`jnl`	Training Binary Neural Networks using the Bayesian Learning Rule. CoRR Xiangming Meng, Roman Bachmann, Mohammad Emtiyaz Khan
2019	—	`conf`	Motion Capture from Pan-Tilt Cameras with Unknown Orientation. 3DV Roman Bachmann, Jörg Spörri, Pascal Fua, Helge Rhodin
2019	J	`jnl`	Motion Capture from Pan-Tilt Cameras with Unknown Orientation. CoRR Roman Bachmann, Jörg Spörri, Pascal Fua, Helge Rhodin