Roman Bachmann
7 papers · 2020–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(22)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
multimodal learning
(2)
representation learning
(1)
continual learning
(1)
image segmentation
(1)
image generation
(1)
variational inference
(1)
pose estimation
(1)
autoregressive generation
(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)
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
NeurIPS 2024
ViPer: Visual Personalization of Generative Models via Individual Preference Learning
ECCV 2024
4M: Massively Multimodal Masked Modeling
NeurIPS 2023
Modality-Invariant Visual Odometry for Embodied Vision
CVPR 2023
MultiMAE: Multi-modal Multi-task Masked Autoencoders
ECCV 2022
Training Binary Neural Networks using the Bayesian Learning Rule
ICML 2020