Roman Bachmann
7 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π£ Hot Topic Early Bird π Conference Polyglot (4) π Academic Marathon (5)
π
Cross-Pollinator
(13)
π
Renaissance Researcher
(5)
πΊοΈ
Taxonomy Completionist
(22)
Conferences
ECCV (2)
ICML (2)
NIPS (2)
CVPR (1)
Top co-authors
Keywords
multimodal learning
(2)
representation learning
(1)
continual learning
(1)
image segmentation
(1)
image generation
(1)
variational inference
(1)
pose estimation
(1)
depth estimation
(1)
sensor fusion
(1)
diffusion model
(1)
feature map
(1)
foundation model
(1)
latent space
(1)
vision-language model
(1)
uncertainty estimation
(1)
vision foundation model
(1)
weight quantization
(1)
masked autoencoder
(1)
discrete tokenization
(1)
any-to-any model
(1)
Papers
FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
ICML 2025
4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities
NIPS 2024
ViPer: Visual Personalization of Generative Models via Individual Preference Learning
ECCV 2024
Modality-Invariant Visual Odometry for Embodied Vision
CVPR 2023
4M: Massively Multimodal Masked Modeling
NIPS 2023
MultiMAE: Multi-modal Multi-task Masked Autoencoders
ECCV 2022
Training Binary Neural Networks using the Bayesian Learning Rule
ICML 2020