Selected Key References

For a more complete list, please see Google Scholar.

Rongzhen Zhao, Wenyan Yang, Juho Kannala, Joni Pajarinen (2026). Smoothing Slot Attention Iterations and Recurrences. International Conference on Machine Learning.

Zhiyuan Li, Rongzhen Zhao, Wenyan Yang, Wenshuai Zhao, Pekka Marttinen, Joni Pajarinen (2026). Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence. International Conference on Machine Learning.

Jatan Shrestha, Santeri Heiskanen, Kari Hepola, Severi Rissanen, Pekka Jääskeläinen, Joni Pajarinen (2026). Pareto-Conditioned Diffusion Models for Offline Multi-Objective Optimization. International Conference on Learning Representations.

PDF Cite Code Poster Slides

Mohammadreza Nakhaei, Aidan Scannell, Joni Pajarinen (2026). Offline Meta-Reinforcement Learning in Piecewise Stationary Environments. Transactions on Machine Learning Research.

Guangyuan Li, Rongzhen Zhao, Jinhong Deng, Yanbo Wang, Joni Pajarinen (2026). Object-Centric Vision Token Pruning for Vision Language Models. IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Yuying Zhang, Kevin Sebastian Luck, Francesco Verdoja, Ville Kyrki, Joni Pajarinen (2026). Modesuite: Robot learning task suite for benchmarking mobile manipulation with deformable objects. IEEE Robotics and Automation Letters.

Vivienne Huiling Wang, Tinghuai Wang, Joni Pajarinen (2026). Learning Multi-Timescale Abstractions for Hierarchical Combinatorial Planning. International Conference on Machine Learning.

Hadrien Crassous, Mohamed Yassine Kabouri, Minahil Raza, Joni Pajarinen, Riad Akrour (2026). Embodied Active Learning under Limited Annotation and Navigation Budget for Object Detection. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Yi Zhao, Aidan Scannell, Wenshuai Zhao, Yuxin Hou, Tianyu Cui, Le Chen, Dieter Buchler, Arno Solin, Juh Kannala, Joni Pajarinen (2026). Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data. International Conference on Learning Representations.

Jaakko Tuomisto, Yuan Zheng, Inshu Chauhan, Olli Seppänen, Joni Pajarinen (2026). Automating on-site object inspection with a quadruped robot and BIM. Automation in Construction.

PDF Cite Slides

Hongjia Liu, Rongzhen Zhao, Haohan Chen, Joni Pajarinen (2025). MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning. Conference on Neural Information Processing Systems (NeurIPS).

PDF Cite Code Slides

Yuying Zhang, Joni Pajarinen (2025). Manipulate-to-Navigate: Reinforcement Learning with Visual Affordances and Manipulability Priors. EEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

PDF Cite Slides

Vivienne Huiling Wang, Tinghuai Wang, Joni Pajarinen (2025). Probabilistic Subgoal Representations for Hierarchical Reinforcement learning. In Proceedings of the International Conference on Machine Learning (ICML).

Wenyan Yang, Ahmet Tikna, Yi Zhao, Yuying Zhang, Luigi Palopoli, Marco Roveri, Joni Pajarinen (2025). Extracting Visual Plans from Unlabeled Videos via Symbolic Guidance. Conference on Robot Learning (CoRL).

PDF Cite Slides

Rongzhen Zhao, Vivienne Wang, Juho Kannala, Joni Pajarinen (2025). Vector-Quantized Vision Foundation Models for Object-Centric Learning. ACM International Conference on Multimedia (ACM MM).

Rongzhen Zhao, Vivienne Wang, Juho Kannala, Joni Pajarinen (2025). Multi-Scale Fusion for Object Representation. International Conference on Learning Representations (ICLR).

Aidan Scannell, Mohammadreza Nakhaei, Kalle Kujanpää, Yi Zhao, Kevin Sebastian Luck, Arno Solin, Joni Pajarinen (2025). Discrete Codebook World Models for Continuous Control. International Conference on Learning Representations (ICLR).

PDF Cite Code Video

Zhiyuan Li, Wenshuai Zhao, Lijun Wu, Joni Pajarinen (2025). AgentMixer: Multi-Agent Correlated Policy Factorization. Proceedings of the AAAI Conference on Artificial Intelligence.

Mohammadreza Nakhaei, Aidan Scannell, Joni Pajarinen (2025). Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence.

Abdolreza Taheri, Amy Rankka, Pelle Gustafsson, Joni Pajarinen, Reza Ghabcheloo (2024). End-Effector Cartesian Velocity Control for Redundant Loader Cranes Using Reinforcement learning. IEEE Transactions on Robotics.

Pascal Klink, Carlo D'Eramo, Jan Peters, Joni Pajarinen (2024). On the benefit of optimal transport for curriculum reinforcement learning. IEEE Transactions on Pattern Analysis and Machine Intelligence.

Wenshuai Zhao, Yi Zhao, Zhiyuan Li, Juho Kannala, Joni Pajarinen (2024). Optimistic Multi-Agent Policy Gradient. In Proceedings of the International Conference on Machine Learning (ICML).

Zhiyuan Li, Wenshuai Zhao, Lijun Wu, Joni Pajarinen, Joni Pajarinen (2024). Backpropagation Through Agents. AAAI Conference on Artificial Intelligence (AAAI).

Yi Zhao, Le Chen, Jan Schneider, Quankai Gao, Juho Kannala, Bernhard Schölkopf, Joni Pajarinen, Dieter Büchler (2024). RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands. Conference on Robot Learning (CoRL).

Aidan Scannell, Riccardo Mereu, Paul Chang, Ella Tamir, Joni Pajarinen, Arno Solin (2024). Function-space Prameterization of Neural Networks for Sequential Learning. The Twelth International Conference on Learning Representations (ICLR).

PDF Cite Code Website

Kalle Kujanpää, Amin Babadi, Yi Zhao, Juho Kannala, Alexander Ilin, Joni Pajarinen (2024). Continuous Monte Carlo Graph Search. International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS).

Vivienne Huiling Wang, Tinghuai Wang, Wenyan Yang, Joni-Kristian Kämäräinen, Joni Pajarinen (2024). Probabilistic Subgoal Representations for Hierarchical Reinforcement learning. In Proceedings of the International Conference on Machine Learning (ICML).

Mohammadreza Nakhaei, Aidan Scannell, Joni Pajarinen (2024). Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning. 4th Annual Conference on Learning for Dynamics and Control (L4DC).

Kalle Kujanpää, Joni Pajarinen, Alexander Ilin (2023). Hybrid search for efficient planning with completeness guarantees. Advances in Neural Information Processing Systems (NeurIPS).

Yi Zhao, Wenshuai Zhao, Rinu Boney, Juho Kannala, Joni Pajarinen (2023). Simplified Temporal Consistency Reinforcement Learning. In Proceedings of the International Conference on Machine Learning (ICML).

Kalle Kujanpää, Joni Pajarinen, Alexander Ilin (2023). Hierarchical Imitation Learning with Vector Quantized Models. In Proceedings of the International Conference on Machine Learning (ICML).

Abdolreza Taheri, Pelle Gustafsson, Marcus Rösth, Reza Ghabcheloo, Joni Pajarinen (2022). Nonlinear Model Learning for Compensation and Feedforward Control of Real-World Hydraulic Actuators Using Gaussian Processes. IEEE Robotics and Automation Letters.

Joni Pajarinen, Jens Lundell, Ville Kyrki (2022). POMDP planning under object composition uncertainty: Application to robotic manipulation. IEEE Transactions on Robotics.

Pascal Klink, Haoyi Yang, Carlo D’Eramo, Joni Pajarinen, Jan Peters (2022). Curriculum reinforcement learning via constrained optimal transport. In Proceedings of the International Conference on Machine Learning (ICML).

Mikko Lauri, David Hsu, Joni Pajarinen (2022). Partially Observable Markov Decision Processes in Robotics: A Survey. IEEE Transactions on Robotics.

Pascal Klink, Carlo D'Eramo, Jan Peters, Joni Pajarinen (2022). Boosted Curriculum Reinforcement Learning. International Conference on Learning Representations (ICLR).

Abdolreza Taheri, Joni Pajarinen, Reza Ghabcheloo (2022). GPU-accelerated policy optimization via batch automatic differentiation of gaussian processes for real-world control. International Conference on Robotics and Automation (ICRA).

Pascal Klink, Hany Abdulsamad, Boris Belousov, Carlo D'Eramo, Jan Peters, Joni Pajarinen (2021). A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning. Journal of Machine Learning Research (JMLR).

Tuan Q Dam, Carlo D'Eramo, Jan Peters, Joni Pajarinen (2021). Convex Regularization in Monte-Carlo Tree Search. In Proceedings of the International Conference on Machine Learning (ICML).

Pascal Klink, Carlo D'Eramo, Jan Peters, Joni Pajarinen (2020). Self-Paced Deep Reinforcement Learning. In Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS).

Tuan Dam, Pascal Klink, Carlo D'Eramo, Jan Peters, Joni Pajarinen (2020). Generalized Mean Estimation in Monte-Carlo Tree Search. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI).

Mikko Lauri, Joni Pajarinen, Jan Peters (2020). Multi-agent active information gathering in discrete and continuous-state decentralized POMDPs by policy graph improvement. Autonomous Agents and Multi-Agent Systems.

Joni Pajarinen, Oleg Arenz, Jan Peters, Gerhard Neumann (2020). Probabilistic approach to physical object disentangling. IEEE Robotics and Automation Letters.

Joni Pajarinen, Hong Linh Thai, Riad Akrour, Jan Peters, Gerhard Neumann (2019). Compatible natural gradient policy search. Machine Learning.

Riad Akrour, Joni Pajarinen, Jan Peters, Gerhard Neumann (2019). Projections for Approximate Policy Iteration Algorithms. In Proceedings of the International Conference on Machine Learning (ICML).

Dorothea Koert, Joni Pajarinen, Albert Schotschneider, Susanne Trick, Constantin Rothkopf, Jan Peters (2019). Learning Intention Aware Online Adaptation of Movement Primitives. IEEE Robotics and Automation Letters.

Takayuki Osa, Joni Pajarinen, Gerhard Neumann, J Andrew Bagnell, Pieter Abbeel, Jan Peters (2018). An Algorithmic Perspective on Imitation Learning. Foundations and Trends in Robotics.

Joni Pajarinen, Ville Kyrki, Michael Koval, Siddhartha Srinivasa, Jan Peters, Gerhard Neumann (2017). Hybrid Control Trajectory Optimization under Uncertainty. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Joni Pajarinen, Ville Kyrki (2017). Robotic manipulation of multiple objects as a POMDP. Artificial Intelligence, Elsevier.