← Authors

Georg Martius

47 papers · 2018–2025 · 7 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (7) πŸƒ Academic Marathon (7) 🌈 Renaissance Researcher (7) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (41) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸ† Grand Slam 🧬 Topic Evolution 🀝 Dynamic Duo (10) πŸ† Keyword Champion (2) πŸ‘‘ Triple Crown πŸ”₯ Unstoppable (8) ⚑ Prolific Year (11) πŸ’Ž Century Club (47) πŸ—ƒοΈ Keyword Collector (118)

Conferences

ICLR (14) NIPS (12) ICML (11) CORL (5) CVPR (3) AAAI (1) ECCV (1)

Top co-authors

Michal Rolinek (10) Sebastian Blaes (7) Marin Vlastelica (6) Maximilian Seitzer (6) Anselm Paulus (6) Marco Bagatella (6) Andrii Zadaianchuk (6) VΓ­t Musil (5) Bernhard SchΓΆlkopf (4) Dominik Zietlow (4)

Keywords

reinforcement learning (5) model-based reinforcement learning (3) model-based planning (3) representation learning (3) variational autoencoder (3) subgoal planning (2) robotic manipulation (2) object-centric learning (2) inductive bia (2) disentangled representation (2) robot manipulation (2) hierarchical reinforcement learning (2) deep reinforcement learning (2) video representation (2) trajectory optimization (2) intrinsic motivation (2) unsupervised learning (2) data efficiency (2) feature extraction (1) variational inference (1)

Papers

Temporally Consistent Object-Centric Learning by Contrasting Slots CVPR 2025
On the Transfer of Object-Centric Representation Learning ICLR 2025
Advancing Out-of-Distribution Detection via Local Neuroplasticity ICLR 2025
Zero-Shot Offline Imitation Learning via Optimal Transport ICML 2025
SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models ICML 2025
Active Fine-Tuning of Multi-Task Policies ICML 2025
Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics ICLR 2024
Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks ICLR 2024
Learning with 3D rotations, a hitchhiker’s guide to SO(3) ICML 2024
Causal Action Influence Aware Counterfactual Data Augmentation ICML 2024
LPGD: A General Framework for Backpropagation through Embedded Optimization Layers ICML 2024
Colored Noise in PPO: Improved Exploration and Performance through Correlated Action Sampling AAAI 2024
Modelling Microbial Communities with Graph Neural Networks ICML 2024
Multi-View Causal Representation Learning with Partial Observability ICLR 2024
The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks. ICLR 2024
DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems ICLR 2023
Benchmarking Offline Reinforcement Learning on Real-Robot Hardware ICLR 2023
Goal-conditioned Offline Planning from Curious Exploration NIPS 2023
Online Learning under Adversarial Nonlinear Constraints NIPS 2023
Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities NIPS 2023
Regularity as Intrinsic Reward for Free Play NIPS 2023
Backpropagation through Combinatorial Algorithms: Identity with Projection Works ICLR 2023
Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning ICLR 2023
Embrace the Gap: VAEs Perform Independent Mechanism Analysis NIPS 2022
Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation NIPS 2022
On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks ICLR 2022
Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks CORL 2022
Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations CORL 2022
Extracting Strong Policies for Robotics Tasks from Zero-Order Trajectory Optimizers ICLR 2021
Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains NIPS 2021
Hierarchical Reinforcement Learning with Timed Subgoals NIPS 2021
Causal Influence Detection for Improving Efficiency in Reinforcement Learning NIPS 2021
Planning from Pixels in Environments with Combinatorially Hard Search Spaces NIPS 2021
Self-supervised Reinforcement Learning with Independently Controllable Subgoals CORL 2021
Risk-Averse Zero-Order Trajectory Optimization CORL 2021
Self-supervised Visual Reinforcement Learning with Object-centric Representations ICLR 2021
CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints ICML 2021
Neuro-algorithmic Policies Enable Fast Combinatorial Generalization ICML 2021
Demystifying Inductive Biases for (Beta-)VAE Based Architectures ICML 2021
Sample-efficient Cross-Entropy Method for Real-time Planning CORL 2020
Differentiation of Blackbox Combinatorial Solvers ICLR 2020
Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers ECCV 2020
Optimizing Rank-Based Metrics With Blackbox Differentiation CVPR 2020
Control What You Can: Intrinsically Motivated Task-Planning Agent NIPS 2019
Variational Autoencoders Pursue PCA Directions (by Accident) CVPR 2019
L4: Practical loss-based stepsize adaptation for deep learning NIPS 2018
Learning Equations for Extrapolation and Control ICML 2018