AIConfPaper
← Search

Stefan Bauer

42 accepted papers

2026

Are Object-Centric Representations Better At Compositional Generalization?

Ferdinand Kapl, Amir Mohammad Karimi Mamaghan, Maximilian Seitzer, Karl Johansson, Carsten Marr, Stefan Bauer +1
ICML 2026poster

Compositional generalization, the ability to reason about novel combinations of familiar concepts, is fundamental to human cognition and a critical challenge for machine learning. Object-centric (OC) representations, which encode a scene as a set of objects, are often argued to support such generali…

Cited by 0Source ↗Scholar ↗
2026

From Growing to Looping: A Unified View of Iterative Computation in LLMs

Ferdinand Kapl, Emmanouil Angelis, Kaitlin Maile, Johannes von Oswald, Stefan Bauer
ICML 2026poster

Looping, reusing a block of layers across depth, and depth growing, training shallow-to-deep models by duplicating middle layers, have both been linked to stronger reasoning, but their relationship remains unclear. We provide a mechanistic unification: looped and depth-grown models exhibit convergen…

Cited by 0Source ↗Scholar ↗
2025

Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models

Amir Mohammad Karimi Mamaghan, Samuele Papa, Karl Henrik Johansson, Stefan Bauer, Andrea Dittadi
ICLR 2025poster

Object-centric (OC) representations, which model visual scenes as compositions of discrete objects, have the potential to be used in various downstream tasks to achieve systematic compositional generalization and facilitate reasoning. However, these claims have yet to be thoroughly validated empiric…

Cited by 8Source ↗PDF ↗Scholar ↗
2025

Preference-Guided Diffusion for Multi-Objective Offline Optimization

Yashas Annadani, Syrine Belakaria, Stefano Ermon, Stefan Bauer, Barbara E Engelhardt
NeurIPS 2025poster

Offline multi-objective optimization aims to identify Pareto-optimal solutions given a dataset of designs and their objective values. In this work, we propose a preference-guided diffusion model that generates Pareto-optimal designs by leveraging a classifier-based guidance mechanism. Our guidance c…

Cited by 0Source ↗Scholar ↗
2024

Amortized Active Causal Induction with Deep Reinforcement Learning

Yashas Annadani, Panagiotis Tigas, Stefan Bauer, Adam Foster
NeurIPS 2024poster

We present Causal Amortized Active Structure Learning (CAASL), an active intervention design policy that can select interventions that are adaptive, real-time and that does not require access to the likelihood. This policy, an amortized network based on the transformer, is trained with reinforcement…

Cited by 2Source ↗PDF ↗Scholar ↗
2024

Challenges and Considerations in the Evaluation of Bayesian Causal Discovery

Amir Mohammad Karimi Mamaghan, Panagiotis Tigas, Karl Henrik Johansson, Yarin Gal, Yashas Annadani, Stefan Bauer
ICML 2024poster

Representing uncertainty in causal discovery is a crucial component for experimental design, and more broadly, for safe and reliable causal decision making. Bayesian Causal Discovery (BCD) offers a principled approach to encapsulating this uncertainty. Unlike non-Bayesian causal discovery, which rel…

Cited by 4Source ↗PDF ↗Scholar ↗
2023

BayesDAG: Gradient-Based Posterior Inference for Causal Discovery

Yashas Annadani, Nick Pawlowski, Joel Jennings, Stefan Bauer, Cheng Zhang, Wenbo Gong
NeurIPS 2023poster

Bayesian causal discovery aims to infer the posterior distribution over causal models from observed data, quantifying epistemic uncertainty and benefiting downstream tasks. However, computational challenges arise due to joint inference over combinatorial space of Directed Acyclic Graphs (DAGs) and n…

Cited by 24Source ↗PDF ↗code ↗Scholar ↗
2023

Benchmarking Offline Reinforcement Learning on Real-Robot Hardware

Nico Gürtler, Sebastian Blaes, Pavel Kolev, Felix Widmaier, Manuel Wuthrich, Stefan Bauer +2
ICLR 2023top-25%

Learning policies from previously recorded data is a promising direction for real-world robotics tasks, as online learning is often infeasible. Dexterous manipulation in particular remains an open problem in its general form. The combination of offline reinforcement learning with large diverse datas…

Cited by 38Source ↗PDF ↗Scholar ↗
2023

DRCFS: Doubly Robust Causal Feature Selection

Francesco Quinzan, Ashkan Soleymani, Patrick Jaillet, Cristian R. Rojas, Stefan Bauer
ICML 2023poster

Knowing the features of a complex system that are highly relevant to a particular target variable is of fundamental interest in many areas of science. Existing approaches are often limited to linear settings, sometimes lack guarantees, and in most cases, do not scale to the problem at hand, in parti…

Cited by 11Source ↗PDF ↗Scholar ↗
2023

Differentiable Multi-Target Causal Bayesian Experimental Design

Panagiotis Tigas, Yashas Annadani, Desi R. Ivanova, Andrew Jesson, Yarin Gal, Adam Foster +1
ICML 2023poster

We introduce a gradient-based approach for the problem of Bayesian optimal experimental design to learn causal models in a batch setting --- a critical component for causal discovery from finite data where interventions can be costly or risky. Existing methods rely on greedy approximations to constr…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2023

Diffusion Based Representation Learning

Sarthak Mittal, Korbinian Abstreiter, Stefan Bauer, Bernhard Schölkopf, Arash Mehrjou
ICML 2023poster

Diffusion-based methods, represented as stochastic differential equations on a continuous-time domain, have recently proven successful as non-adversarial generative models. Training such models relies on denoising score matching, which can be seen as multi-scale denoising autoencoders. Here, we augm…

Cited by 35Source ↗PDF ↗Scholar ↗
2023

DiscoBAX - Discovery of optimal intervention sets in genomic experiment design

Clare Lyle, Arash Mehrjou, Pascal Notin, Andrew Jesson, Stefan Bauer, Yarin Gal +1
ICML 2023poster

The discovery of therapeutics to treat genetically-driven pathologies relies on identifying genes involved in the underlying disease mechanism. Existing approaches search over the billions of potential interventions to maximize the expected influence on the target phenotype. However, to reduce the r…

Cited by 12Source ↗PDF ↗code ↗Scholar ↗
2023

Structure by Architecture: Structured Representations without Regularization

Felix Leeb, Giulia Lanzillotta, Yashas Annadani, Michel Besserve, Stefan Bauer, Bernhard Schölkopf
ICLR 2023poster

We study the problem of self-supervised structured representation learning using autoencoders for downstream tasks such as generative modeling. Unlike most methods which rely on matching an arbitrary, relatively unstructured, prior distribution for sampling, we propose a sampling technique that reli…

Cited by 9Source ↗PDF ↗Scholar ↗
2023

Trust Your $\nabla$: Gradient-based Intervention Targeting for Causal Discovery

Mateusz Olko, Michał Zając, Aleksandra Nowak, Nino Scherrer, Yashas Annadani, Stefan Bauer +2
NeurIPS 2023poster

Inferring causal structure from data is a challenging task of fundamental importance in science. Often, observational data alone is not enough to uniquely identify a system’s causal structure. The use of interventional data can address this issue, however, acquiring these samples typically demands a…

Cited by 6Source ↗PDF ↗Scholar ↗
2022

Adaptive Gaussian Process Change Point Detection

Edoardo Caldarelli, Philippe Wenk, Stefan Bauer, Andreas Krause
ICML 2022spotlight

Detecting change points in time series, i.e., points in time at which some observed process suddenly changes, is a fundamental task that arises in many real-world applications, with consequences for safety and reliability. In this work, we propose ADAGA, a novel Gaussian process-based solution to th…

Cited by 15Source ↗PDF ↗Scholar ↗
2022

Bayesian structure learning with generative flow networks

Tristan Deleu, António Góis, Chris Emezue, Mansi Rankawat, Simon Lacoste-Julien, Stefan Bauer +1
UAI 2022poster

In Bayesian structure learning, we are interested in inferring a distribution over the directed acyclic graph (DAG) structure of Bayesian networks, from data. Defining such a distribution is very challenging, due to the combinatorially large sample space, and approximations based on MCMC are often r…

Cited by 169Source ↗PDF ↗code ↗Scholar ↗
2022

Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation

Niklas Funk, Charles B. Schaff, Rishabh Madan, Takuma Yoneda, Julen Urain De Jesus, Joe Watson +7
RA-L 2022

Dexterous manipulation is a challenging and important problem in robotics. While data-driven methods are a promising approach, current benchmarks require simulation or extensive engineering support due to the sample inefficiency of popular methods. We present benchmarks for the TriFinger system, an

Cited by 39Source ↗code ↗Scholar ↗
2022

Exploring the Latent Space of Autoencoders with Interventional Assays

Felix Leeb, Stefan Bauer, Michel Besserve, Bernhard Schölkopf
NeurIPS 2022accept

Autoencoders exhibit impressive abilities to embed the data manifold into a low-dimensional latent space, making them a staple of representation learning methods. However, without explicit supervision, which is often unavailable, the representation is usually uninterpretable, making analysis and pri…

Cited by 18Source ↗PDF ↗code ↗Scholar ↗
2022

GeneDisco: A Benchmark for Experimental Design in Drug Discovery

Arash Mehrjou, Ashkan Soleymani, Andrew Jesson, Pascal Notin, Yarin Gal, Stefan Bauer +1
ICLR 2022poster

In vitro cellular experimentation with genetic interventions, using for example CRISPR technologies, is an essential step in early-stage drug discovery and target validation that serves to assess initial hypotheses about causal associations between biological mechanisms and disease pathologies. With…

Cited by 27Source ↗PDF ↗code ↗Scholar ↗
2022

Interventions, Where and How? Experimental Design for Causal Models at Scale

Panagiotis Tigas, Yashas Annadani, Andrew Jesson, Bernhard Schölkopf, Yarin Gal, Stefan Bauer
NeurIPS 2022accept

Causal discovery from observational and interventional data is challenging due to limited data and non-identifiability which introduces uncertainties in estimating the underlying structural causal model (SCM). Incorporating these uncertainties and selecting optimal experiments (interventions) to per…

Cited by 49Source ↗PDF ↗code ↗Scholar ↗
2022

The Role of Pretrained Representations for the OOD Generalization of RL Agents

Frederik Träuble, Andrea Dittadi, Manuel Wuthrich, Felix Widmaier, Peter Vincent Gehler, Ole Winther +4
ICLR 2022poster

Building sample-efficient agents that generalize out-of-distribution (OOD) in real-world settings remains a fundamental unsolved problem on the path towards achieving higher-level cognition. One particularly promising approach is to begin with low-dimensional, pretrained representations of our world…

Cited by 13Source ↗PDF ↗Scholar ↗
2022

Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger

Arthur Allshire, Mayank MittaI, Varun Lodaya, Viktor Makoviychuk, Denys Makoviichuk, Felix Widmaier +4
IROS 2022poster

In-hand manipulation of objects is an important capability to enable robots to carry-out tasks which demand high levels of dexterity. This work presents a robot systems approach to learning dexterous manipulation tasks involving moving objects to arbitrary 6-DoF poses. We show empirical benefits, bo…

Cited by 77Source ↗code ↗Scholar ↗
2021

CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning

Ossama Ahmed, Frederik Träuble, Anirudh Goyal, Alexander Neitz, Manuel Wuthrich, Yoshua Bengio +2
ICLR 2021poster

Despite recent successes of reinforcement learning (RL), it remains a challenge for agents to transfer learned skills to related environments. To facilitate research addressing this problem, we proposeCausalWorld, a benchmark for causal structure and transfer learning in a robotic manipulation envir…

Cited by 161Source ↗PDF ↗Scholar ↗
2021

Function Contrastive Learning of Transferable Meta-Representations

Muhammad Waleed Gondal, Shruti Joshi, Nasim Rahaman, Stefan Bauer, Manuel Wuthrich, Bernhard Schölkopf
ICML 2021spotlight

Meta-learning algorithms adapt quickly to new tasks that are drawn from the same task distribution as the training tasks. The mechanism leading to fast adaptation is the conditioning of a downstream predictive model on the inferred representation of the task’s underlying data generative process, or…

Cited by 24Source ↗PDF ↗Scholar ↗
2021

On Disentangled Representations Learned from Correlated Data

Frederik Träuble, Elliot Creager, Niki Kilbertus, Francesco Locatello, Andrea Dittadi, Anirudh Goyal +2
ICML 2021oral

The focus of disentanglement approaches has been on identifying independent factors of variation in data. However, the causal variables underlying real-world observations are often not statistically independent. In this work, we bridge the gap to real-world scenarios by analyzing the behavior of the…

Cited by 142Source ↗PDF ↗code ↗Scholar ↗
2021

On the Transfer of Disentangled Representations in Realistic Settings

Andrea Dittadi, Frederik Träuble, Francesco Locatello, Manuel Wuthrich, Vaibhav Agrawal, Ole Winther +2
ICLR 2021poster

Learning meaningful representations that disentangle the underlying structure of the data generating process is considered to be of key importance in machine learning. While disentangled representations were found to be useful for diverse tasks such as abstract reasoning and fair classification, the…

Cited by 95Source ↗PDF ↗Scholar ↗
2021

Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling

Đorđe Miladinović, Aleksandar Stanić, Stefan Bauer, Jürgen Schmidhuber, Joachim M. Buhmann
ICLR 2021poster

How to improve generative modeling by better exploiting spatial regularities and coherence in images? We introduce a novel neural network for building image generators (decoders) and apply it to variational autoencoders (VAEs). In our spatial dependency networks (SDNs), feature maps at each level of…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗
2021

Spatially Structured Recurrent Modules

Nasim Rahaman, Anirudh Goyal, Muhammad Waleed Gondal, Manuel Wuthrich, Stefan Bauer, Yash Sharma +2
ICLR 2021poster

Capturing the structure of a data-generating process by means of appropriate inductive biases can help in learning models that generalise well and are robust to changes in the input distribution. While methods that harness spatial and temporal structures find broad application, recent work has demon…

Cited by 4Source ↗PDF ↗Scholar ↗
2021

Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning

Nan Rosemary Ke, Aniket Rajiv Didolkar, Sarthak Mittal, Anirudh Goyal, Guillaume Lajoie, Stefan Bauer +4
NeurIPS 2021poster

Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the premise that the causal variables themselves are observed. However, for AI agents such as robots trying to make sense of their environment, the only observables are low-l…

Cited by 52Source ↗code ↗Scholar ↗
2020

A Real-Robot Dataset for Assessing Transferability of Learned Dynamics Models

Diego Agudelo-España, Andrii Zadaianchuk, Philippe Wenk, Aditya Garg, Joel Akpo, Felix Grimminger +8
ICRA 2020poster

In the context of model-based reinforcement learning and control, a large number of methods for learning system dynamics have been proposed in recent years. The purpose of these learned models is to synthesize new control policies. An important open question is how robust current dynamics-learning m…

Cited by 10Source ↗Scholar ↗
2020

Bayesian Online Prediction of Change Points

Diego Agudelo-España, Sebastian Gomez-Gonzalez, Stefan Bauer, Bernhard Schölkopf, Jan Peters
UAI 2020poster

Online detection of instantaneous changes in the generative process of a data sequence generally focuses on retrospective inference of such change points without considering their future occurrences. We extend the Bayesian Online Change Point Detection algorithm to also infer the number of time step…

Cited by 43Source ↗PDF ↗code ↗Scholar ↗
2020

Disentangling Factors of Variations Using Few Labels

Francesco Locatello, Michael Tschannen, Stefan Bauer, Gunnar Rätsch, Bernhard Schölkopf, Olivier Bachem
ICLR 2020poster

Learning disentangled representations is considered a cornerstone problem in representation learning. Recently, Locatello et al. (2019) demonstrated that unsupervised disentanglement learning without inductive biases is theoretically impossible and that existing inductive biases and unsupervised met…

Cited by 210Source ↗Scholar ↗
2020

TriFinger: An Open-Source Robot for Learning Dexterity

Manuel Wuthrich, Felix Widmaier, Felix Grimminger, Shruti Joshi, Vaibhav Agrawal, Bilal Hammoud +8
CoRL 2020

Dexterous object manipulation is still an open problem in robotics, despite the rapid progress in machine learning during the past decade. We argue that a key issue which has hindered progress is the high cost of experimentation on real systems, in terms of both time and money. We address this probl

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2019

AReS and MaRS Adversarial and MMD-Minimizing Regression for SDEs

Gabriele Abbati, Philippe Wenk, Michael A. Osborne, Andreas Krause, Bernhard Schölkopf, Stefan Bauer
ICML 2019oral

Stochastic differential equations are an important modeling class in many disciplines. Consequently, there exist many methods relying on various discretization and numerical integration schemes. In this paper, we propose a novel, probabilistic model for estimating the drift and diffusion given noisy…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗
2019

Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations

Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Raetsch, Sylvain Gelly, Bernhard Schölkopf +1
ICML 2019oral

The key idea behind the unsupervised learning of disentangled representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this paper, we provide a sober look at recent progress in the field and challeng…

Cited by 1772Source ↗PDF ↗code ↗Scholar ↗
2019

Fast Gaussian process based gradient matching for parameter identification in systems of nonlinear ODEs

Philippe Wenk, Alkis Gotovos, Stefan Bauer, Nico S. Gorbach, Andreas Krause, Joachim M. Buhmann
AISTATS 2019poster

Parameter identification and comparison of dynamical systems is a challenging task in many fields. Bayesian approaches based on Gaussian process regression over time-series data have been successfully applied to infer the parameters of a dynamical system without explicitly solving it. While the bene…

Cited by 55Source ↗PDF ↗code ↗Scholar ↗
2019

On the Fairness of Disentangled Representations

Francesco Locatello, Gabriele Abbati, Thomas Rainforth, Stefan Bauer, Bernhard Schölkopf, Olivier Bachem
NeurIPS 2019poster

Recently there has been a significant interest in learning disentangled representations, as they promise increased interpretability, generalization to unseen scenarios and faster learning on downstream tasks. In this paper, we investigate the usefulness of different notions of disentanglement for i…

Cited by 267Source ↗PDF ↗Scholar ↗
2019

On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset

Muhammad Waleed Gondal, Manuel Wuthrich, Djordje Miladinovic, Francesco Locatello, Martin Breidt, Valentin Volchkov +4
NeurIPS 2019poster

Learning meaningful and compact representations with disentangled semantic aspects is considered to be of key importance in representation learning. Since real-world data is notoriously costly to collect, many recent state-of-the-art disentanglement models have heavily relied on synthetic toy data-s…

Cited by 152Source ↗PDF ↗code ↗Scholar ↗
2019

Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness

Raphael Suter, Djordje Miladinovic, Bernhard Schölkopf, Stefan Bauer
ICML 2019oral

The ability to learn disentangled representations that split underlying sources of variation in high dimensional, unstructured data is important for data efficient and robust use of neural networks. While various approaches aiming towards this goal have been proposed in recent times, a commonly acce…

Cited by 192Source ↗PDF ↗Scholar ↗
2017

Efficient and Flexible Inference for Stochastic Systems

Stefan Bauer, Nico S Gorbach, Djordje Miladinovic, Joachim M Buhmann
NeurIPS 2017poster

Many real world dynamical systems are described by stochastic differential equations. Thus parameter inference is a challenging and important problem in many disciplines. We provide a grid free and flexible algorithm offering parameter and state inference for stochastic systems and compare our appro…

Cited by 9Source ↗PDF ↗Scholar ↗