AIConfPaper
← Search

Matthias Bauer

13 accepted papers

2026

Position: Agentic AI systems should be making Bayes-consistent decisions

Theodore Papamarkou, Pierre Alquier, Matthias Bauer, Wray Buntine, Andrew Davison, Gintare Karolina Dziugaite +24
ICML 2026poster

LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to consult, or how many resources to invest. While the usefulness and feasibility of Bayesian approaches remain unclear for L…

Cited by 0Source ↗Scholar ↗
2025

Good, Cheap, and Fast: Overfitted Image Compression with Wasserstein Distortion

Jona Ballé, Luca Versari, Emilien Dupont, Hyunjik Kim, Matthias Bauer
CVPR 2025highlight

Inspired by the success of generative image models, recent work on learned image compression increasingly focuses on better probabilistic models of the natural image distribution, leading to excellent image quality. This, however, comes at the expense of a computational complexity that is several or…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2024

C3: High-Performance and Low-Complexity Neural Compression from a Single Image or Video

Hyunjik Kim, Matthias Bauer, Lucas Theis, Jonathan Richard Schwarz, Emilien Dupont
CVPR 2024poster

Most neural compression models are trained on large datasets of images or videos in order to generalize to unseen data. Such generalization typically requires large and expressive architectures with a high decoding complexity. Here we introduce C3 a neural compression method with strong rate-distort…

Cited by 29Source ↗PDF ↗Scholar ↗
2024

Evaluating Numerical Reasoning in Text-to-Image Models

Ivana Kajic, Olivia Wiles, Isabela Albuquerque, Matthias Bauer, Su Wang, Jordi Pont-Tuset +1
NeurIPS 2024poster

Text-to-image generative models are capable of producing high-quality images that often faithfully depict concepts described using natural language. In this work, we comprehensively evaluate a range of text-to-image models on numerical reasoning tasks of varying difficulty, and show that even the mo…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

Improving fine-grained understanding in image-text pre-training

Ioana Bica, Anastasija Ilic, Matthias Bauer, Goker Erdogan, Matko Bošnjak, Christos Kaplanis +5
ICML 2024poster

We introduce SPARse fine-grained Contrastive alignment (SPARC), a simple method for pretraining more fine-grained multimodal representations from image-text pairs. Given that multiple image patches often correspond to single words, we propose to learn a grouping of image patches for every token in t…

Cited by 16Source ↗PDF ↗Scholar ↗
2021

Improving predictions of Bayesian neural nets via local linearization

Alexander Immer, Maciej Korzepa, Matthias Bauer
AISTATS 2021poster

The generalized Gauss-Newton (GGN) approximation is often used to make practical Bayesian deep learning approaches scalable by replacing a second order derivative with a product of first order derivatives. In this paper we argue that the GGN approximation should be understood as a local linearizatio…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2021

Laplace Redux - Effortless Bayesian Deep Learning

Erik Daxberger, Agustinus Kristiadi, Alexander Immer, Runa Eschenhagen, Matthias Bauer, Philipp Hennig
NeurIPS 2021poster

Bayesian formulations of deep learning have been shown to have compelling theoretical properties and offer practical functional benefits, such as improved predictive uncertainty quantification and model selection. The Laplace approximation (LA) is a classic, and arguably the simplest family of appro…

Cited by 392Source ↗PDF ↗Scholar ↗
2021

Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning

Alexander Immer, Matthias Bauer, Vincent Fortuin, Gunnar Rätsch, Khan Mohammad Emtiyaz
ICML 2021spotlight

Marginal-likelihood based model-selection, even though promising, is rarely used in deep learning due to estimation difficulties. Instead, most approaches rely on validation data, which may not be readily available. In this work, we present a scalable marginal-likelihood estimation method to select…

Cited by 136Source ↗PDF ↗code ↗Scholar ↗
2019

Meta-Learning Probabilistic Inference for Prediction

Jonathan Gordon, John Bronskill, Matthias Bauer, Sebastian Nowozin, Richard Turner
ICLR 2019poster

This paper introduces a new framework for data efficient and versatile learning. Specifically: 1) We develop ML-PIP, a general framework for Meta-Learning approximate Probabilistic Inference for Prediction. ML-PIP extends existing probabilistic interpretations of meta-learning to cover a broad class…

Cited by 330Source ↗PDF ↗code ↗Scholar ↗
2018

Learning Invariances using the Marginal Likelihood

Mark van der Wilk, Matthias Bauer, ST John, James Hensman
NeurIPS 2018poster

In many supervised learning tasks, learning what changes do not affect the predic-tion target is as crucial to generalisation as learning what does. Data augmentationis a common way to enforce a model to exhibit an invariance: training data is modi-fied according to an invariance designed by a human…

Cited by 103Source ↗PDF ↗code ↗Scholar ↗
2016

Understanding Probabilistic Sparse Gaussian Process Approximations

Matthias Bauer, Mark van der Wilk, Carl Edward Rasmussen
NeurIPS 2016poster

Good sparse approximations are essential for practical inference in Gaussian Processes as the computational cost of exact methods is prohibitive for large datasets. The Fully Independent Training Conditional (FITC) and the Variational Free Energy (VFE) approximations are two recent popular methods.…

Cited by 286Source ↗PDF ↗Scholar ↗