CV

Research Experience

• PhD Student / Research Assistant, Autonomous Learning Robots (ALR) Lab, Institute for Anthropomatics and Robotics (IAR), Karlsruhe Institute of Technology, Germany (Apr. 2023 – present)
  • Topic: Interactive Reinforcement Learning with Demonstrations and Preferences
  • Member of the Collaborative Research Center SFB 1574 “Circular Factory for the Perpetual Product”
  • Supervisor: Prof. Dr. Gerhard Neumann
• Visiting Researcher, Cambridge Resilient Autonomous Learning (CamRAL) Lab, University of Cambridge, United Kingdom (Oct. 2025 – Feb. 2026)
  • Research stay hosted by Dr. Rika Antonova
• PhD Student, Bosch Center for Artificial Intelligence, Renningen, Germany (Jan. 2020 – Mar. 2023)
  • Project: Robot Learning from Human Feedback
  • Supervisor: Dr. Andras Gabor Kupcsik, with academic supervision from Prof. Dr. Gerhard Neumann (KIT)
• Early Stage Researcher, Institut de Robòtica i Informàtica Industrial, CSIC-UPC, Barcelona, Spain (Apr. 2017 – Oct. 2019)
  • Topic: Robot adaptation through multimodal interaction and learning (EU H2020 project SOCRATES: Social Cognitive Robotics in the European Society)
  • Supervisor: Prof. Dr. Carme Torras
• Research Intern, Robotics Laboratory, Mihajlo Pupin Institute, Belgrade, Serbia (2015 & 2016 – 2017)
  • Simulations of the Romeo robot performing manipulation tasks in Gazebo; programming the NAO robot in Python

Education

• M.Sc. in Electrical Engineering and Computing, School of Electrical Engineering, University of Belgrade (2015 – 2016)
  • Module: Signals and Systems (60 ECTS), GPA: 10.00 / 10.00
  • Thesis: “Localizing a Mobile Robot Using a Visual Simultaneous Localization and Mapping Algorithm”
• B.Sc. in Electrical Engineering and Computing, School of Electrical Engineering, University of Belgrade (2011 – 2015)
  • Module: Signals and Systems (240 ECTS), GPA: 9.85 / 10.00, best graduate student on the module
  • Thesis: “Mapping and Optimized Path Planning for NAO Robot”

Awards & Scholarships

• Award for Best Graduate Student in the Generation (Signals and Systems module), School of Electrical Engineering, University of Belgrade
• Academician Dragoslav Srejović Award, City of Kragujevac (best students)
• Scholarship for Exceptionally Gifted Students, Ministry of Education, Science and Technological Development of Serbia
• Scholarship for Best Graduating Students, Fund for Talented Youth of the Republic of Serbia (B.Sc. and M.Sc.)

Skills

• Technical: Python, C/C++, PyTorch, JAX, NumPy, Git, Linux, SLURM, HPC clusters
• Languages: English & German (advanced), Spanish (intermediate), Serbian (native)

Teaching & Mentoring

• Teaching assistant for Reinforcement Learning (KIT)
• Supervision of B.Sc./M.Sc. theses and Praktikum projects

Service

• Reviewer for ICLR, NeurIPS, ICML, CoRL, ICRA, IROS
• Co-organized the CoRL 2022 workshop on inductive bias in robot learning

Publications

PAWS: Preference Learning with Advantage-Weighted Segments

Aleksandar Taranovic, Onur Celik, Niklas Freymuth, Ge Li, Serge Thilges, Huy Le, Tai Hoang, Rania Rayyes, Gerhard Neumann. (2026). "PAWS: Preference Learning with Advantage-Weighted Segments." International Conference on Machine Learning (ICML).

Scaffolding Dexterous Manipulation with Vision-Language Models

Vincent de Bakker, Joey Hejna, Tyler Ga Wei Lum, Onur Celik, Aleksandar Taranovic, Denis Blessing, Gerhard Neumann, Jeannette Bohg, Dorsa Sadigh. (2025). "Scaffolding Dexterous Manipulation with Vision-Language Models." Conference on Neural Information Processing Systems (NeurIPS).

AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction

Niklas Freymuth, Tobias Wuerth, Nicolas Schreiber, Balazs Gyenes, Andreas Boltres, Johannes Mitsch, Aleksandar Taranovic, Tai Hoang, Philipp Dahlinger, Philipp Becker, Luise Kaerger, Gerhard Neumann. (2025). "AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction." Conference on Neural Information Processing Systems (NeurIPS).

Towards Fusing Point Cloud and Visual Representations for Imitation Learning

Atalay Donat, Xiaogang Jia, Xi Huang, Aleksandar Taranovic, Denis Blessing, Ge Li, Hongyi Zhou, Hanyi Zhang, Rudolf Lioutikov, Gerhard Neumann. (2025). "Towards Fusing Point Cloud and Visual Representations for Imitation Learning." arXiv preprint arXiv:2502.12320.

Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts

Onur Celik, Aleksandar Taranovic, Gerhard Neumann. (2024). "Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts." International Conference on Machine Learning (ICML).

Domain-Specific Fine-Tuning of Large Language Models for Interactive Robot Programming

Benjamin Alt, Urs Kessner, Aleksandar Taranovic, Darko Katic, Andreas Hermann, Rainer Jaekel, Gerhard Neumann. (2024). "Domain-Specific Fine-Tuning of Large Language Models for Interactive Robot Programming." European Robotics Forum (ERF).

Adversarial Imitation Learning with Preferences

Aleksandar Taranovic, Andras Gabor Kupcsik, Niklas Freymuth, Gerhard Neumann. (2023). "Adversarial Imitation Learning with Preferences." International Conference on Learning Representations (ICLR).

Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors

Niklas Freymuth, Nicolas Schreiber, Aleksandar Taranovic, Philipp Becker, Gerhard Neumann. (2022). "Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors." Conference on Robot Learning (CoRL).

Automatic Learning of Cognitive Exercises for Socially Assistive Robotics

Alejandro Suarez-Hernandez, Antonio Andriella, Aleksandar Taranovic, Javier Segovia-Aguas, Carme Torras, Guillem Alenya. (2021). "Automatic Learning of Cognitive Exercises for Socially Assistive Robotics." IEEE International Conference on Robot and Human Interactive Communication (RO-MAN).

Adaptive Modality Selection Algorithm in Robot-Assisted Cognitive Training

Aleksandar Taranovic, Aleksandar Jevtic, Carme Torras. (2018). "Adaptive Modality Selection Algorithm in Robot-Assisted Cognitive Training." IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Resource-Based Modality Selection in Robot-Assisted Cognitive Training

Aleksandar Taranovic, Aleksandar Jevtic, Joan Hernandez-Farigola, Natalia Tantinya, Carla Abdelnour, Carme Torras. (2018). "Resource-Based Modality Selection in Robot-Assisted Cognitive Training." Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction.

Adaptable Multimodal Interaction Framework for Robot-Assisted Cognitive Training

Aleksandar Taranovic, Aleksandar Jevtic, Carme Torras. (2018). "Adaptable Multimodal Interaction Framework for Robot-Assisted Cognitive Training." Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction.