Research Experience
- Doctoral Researcher, Max Planck Institute for Informatics (Oct. 2025 – Jul. 2026)
- Completed two Research Immersion Labs under the supervision of Prof. Jan Eric Lenssen and Dr. Marc Habermann.
- Investigated self-supervised continuous latent-action representations learned from human videos and their potential use in downstream robot action generation.
- Studied whether compact representations of visual transitions preserve the task-relevant information required for sequential decisions.
- Evaluated learned representations through reconstruction, retrieval, and robot-manipulation experiments, using representation learning together with diffusion- and flow-matching-based action modeling.
- This work motivated my broader interest in representation sufficiency, long-horizon decision-making, compositional generalization, and failure analysis in learned autonomous systems.
- Undergraduate Student Researcher, AI Lab, METU BILTIR Center (Jul. 2023 – Jun. 2025)
- Supervisor: Prof. Seyda Ertekin
- Developed SLLMBO, a sequential hyperparameter-optimization framework combining LLM-guided configuration proposals with Tree-structured Parzen Estimation.
- Evaluated four LLMs across 14 classification and regression tasks; the proposed LLM-TPE sampler achieved better results than the evaluated Bayesian-optimization methods on 9 tasks.
- Computer Vision Research Intern, Computational Biomedicine Lab, University of Houston (Jul. 2022 – Sep. 2022)
- Supervisor: Prof. Ioannis Kakadiaris
- Worked on human detection from UAV imagery under varying viewpoints, distances, and weather conditions using feature pyramid networks.
- Worked on face representation and clustering using FaceNet embeddings and FAISS for efficient similarity-based analysis.