You are here: Home People Iman Nematollahi

Iman Nematollahi

nematoli Postdoctoral Researcher
Postal address:

Albert-Ludwigs-Universität Freiburg
Technische Fakultät
Robot Learning Lab
Georges-Köhler-Allee 080
D-79110 Freiburg i. Br., Germany

Office: Building 80, Room 00-023
Email: nematoli@cs.uni-freiburg.de
Phone: +49 761 203-8023
Personal Website: https://imanema.com

About me

  • 04/2025 - current: Postdoctoral Researcher at Robot Learning Lab, University of Freiburg
  • 01/2024 - 06/2024: Visiting PhD Student at Oxford Robotics Institute, University of Oxford
  • 01/2019 - 12/2024: PhD student at Autonomous Intelligent Systems, University of Freiburg
  • 10/2015 - 11/2018: M.Sc. in Embedded Systems Engineering, University of Freiburg
  • 09/2010 - 05/2015: B.Sc. in Electrical Engineering, Shahid Beheshti University

Research Interests

  • World Models
  • Reinforcement Learning
  • Robotic Manipulation

Publications

  • LUMOS: Language-Conditioned Imitation Learning with World Models
    Iman Nematollahi, Branton DeMoss, Akshay L Chandra, Nick Hawes, Wolfram Burgard, Ingmar Posner
    IEEE ICRA, Atlanta, USA, 2025. [pdf] [website] [video]
  • Bayesian Optimization for Sample-Efficient Policy Improvement in Robotic Manipulation
    Adrian Röfer, Iman Nematollahi, Tim Welschehold, Wolfram Burgard, Abhinav Valada
    IEEE/RSJ IROS, Abu Dhabi, UAE, 2024. [pdf] [website] [video]
  • Robot Skill Generalization via Keypoint Integrated Soft Actor-Critic Gaussian Mixture Models
    Iman Nematollahi*, Kirill Yankov*, Wolfram Burgard, Tim Welschehold
    ISER, Chiang Mai, Thailand, 2023. [pdf] [website] [video]
  • T3VIP: Transformation-based 3D Video Prediction
    Iman Nematollahi, Erick Rosete-Beas, Seyed Mahdi B. Azad, Raghu Rajan, Frank Hutter, Wolfram Burgard
    IEEE/RSJ IROS, Kyoto, Japan, 2022. [pdf] [website] [video]
  • Robot Skill Adaptation via Soft Actor-Critic Gaussian Mixture Models
    Iman Nematollahi*, Erick Rosete-Beas*, Adrian Röfer, Tim Welschehold, Abhinav Valada, Wolfram Burgard
    IEEE ICRA, Philadelphia, USA, 2022. [pdf] [website] [video]
  • Hindsight for Foresight: Unsupervised Structured Dynamics Models from Physical Interaction
    Iman Nematollahi, Oier Mees, Lukas Hermann, Wolfram Burgard
    IEEE/RSJ IROS, Las Vegas, USA, 2020. [pdf] [website] [video]
  • Augmenting Action Model Learning by Non-Geometric Features
    Iman Nematollahi, Daniel Kuhner, Tim Welschehold, Wolfram Burgard
    IEEE ICRA, Montreal, Canada, 2019. [pdf] [video]

Teaching

Past Students

  • Fine-Tuning Diffusion Policies with World Models, 2025, Master's Thesis of Akshay L Chandra
  • Transfer Robot Skills in Reinforcement Learning by Learning Keypoints, 2023, Master's Thesis of Kirill Yankov
  • Task-Agnostic State Value for Visual Planning in 3D World Models, 2022, Master's Thesis of Seyed Mahdi B. Azad
  • Action-Conditioned Video Prediction with 3D Images, 2021, Bachelor's Thesis of Jens Rahnfeld
  • Towards Unsupervised Scene Decomposition, 2021, Master's Project of Leonhard Sommer
  • Deep Reinforcement Learning for Adapting Dynamical Systems, 2021, Master's Project of Erick Rosete Beas