Can Mizrakli

MSc Computer Science at Karlsruhe Institute of Technology

can-mizrakli.jpeg

I’m an MSc Computer Science student at the Karlsruhe Institute of Technology (KIT), working on robot learning.

I work at the Intuitive Robots Lab under Prof. Rudolf Lioutikov on memory-based imitation learning, and as a research assistant at the CV:HCI Lab and H²T on adapting VLA models to new robot embodiments such as the ARMAR-6/7 humanoids and bimanual Franka platforms.

Research interests

  • Robot learning, imitation learning, and robot manipulation
  • Vision-language-action foundation models
  • State space models and memory for long-horizon control
  • Reinforcement learning for robotics

Current work

State space model–based imitation learning at the Intuitive Robots Lab (IRL), with Pankhuri Vanjani and TT-Prof. Dr. Rudolf Lioutikov. Developing a vision-language-action policy for long-horizon robotic manipulation, with recurrent memory for partially observable tasks and a flow-matching action head. Results and a preprint will be released soon.

Robot embodiment adaptation at CV:HCI / H²T, with Dr.-Ing. David Schneider. Supporting VLA adaptation for ARMAR-6/7 humanoids and bimanual Franka Emika platforms through Isaac Sim workflows, hardware interfacing, and teleoperation.

Read more about my research →

Publications

  1. TDSal: Task-Based Top-Down Saliency Prediction Model
    Can Mizrakli and Tolga K Capin
    In CGI 2026, LNCS Proceedings (to appear), 2026