Vincent Fortuin
18 papers · 2019–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Academic Marathon (6) π Interdisciplinary Bridge π Conference Polyglot (7) π§ Keyword Pioneer π Cross-Pollinator (15)
π
Cross-Pollinator
(15)
π
Renaissance Researcher
(5)
π
Keyword Champion
(2)
π₯
Mega-Team
(25)
π¬
Deep Specialist
(10)
β
The Questioner
π
Century Club
(18)
β‘
Prolific Year
(5)
π₯
Unstoppable
(7)
Conferences
ICML (5)
NIPS (4)
ICLR (3)
AISTATS (2)
UAI (2)
ACL (1)
JMLR (1)
Top co-authors
Research topics
Keywords
laplace approximation
(4)
marginal likelihood
(3)
bayesian neural network
(3)
gaussian process
(3)
bayesian inference
(3)
data augmentation
(2)
inductive bia
(2)
variational autoencoder
(2)
uncertainty estimation
(2)
uncertainty quantification
(2)
probabilistic modeling
(1)
epistemic uncertainty
(1)
neural network sparsification
(1)
contextual representation
(1)
model selection
(1)
dimensionality reduction
(1)
invariance learning
(1)
hyperparameter optimization
(1)
representation learning
(1)
pac-bayes theory
(1)
Papers
Can Transformers Learn Full Bayesian Inference in Context?
ICML 2025
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
ICML 2024
Improving Neural Additive Models with Bayesian Principles
ICML 2024
Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks using the Marginal Likelihood
NIPS 2024
FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning
NIPS 2024
Understanding Pathologies of Deep Heteroskedastic Regression
UAI 2024
Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice
JMLR 2023
Bayesian Neural Network Priors Revisited
ICLR 2022
Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations
NIPS 2022
Probing as Quantifying Inductive Bias
ACL 2022
Data augmentation in Bayesian neural networks and the cold posterior effect
UAI 2022
Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning
ICML 2021
Repulsive Deep Ensembles are Bayesian
NIPS 2021
PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees
ICML 2021
Scalable Gaussian Process Variational Autoencoders
AISTATS 2021
Conservative Uncertainty Estimation By Fitting Prior Networks
ICLR 2020
GP-VAE: Deep Probabilistic Time Series Imputation
AISTATS 2020
SOM-VAE: Interpretable Discrete Representation Learning on Time Series
ICLR 2019