→ 09.11.2024: I joined Robust Intelligence (acquired by Cisco in August 2024) as a research intern, where my focus is on secure AI, specifically enhancing the robustness of LLMs against adversarial attacks.

→ 05.28.2024: I’ve started at Google NYC as a research intern! My focus will be on the robustness of LLMs in in-context learning.

→ 01.24.2024: Our study on off-policy deep reinforcement learning has been accepted to Transactions on Machine Learning Research.

→ 10.13.2023: We have presented our work at International Conference on Multimodal Interaction. We have developed an RL framework for one-shot learning of an intent classification task.

→ 10.08.2023: Our paper has been accepted to the Neural Processing Letters. We show that the current techniques lead to the same expected underestimation bias in TD learning. Our simple yet effective approach (nearly) eliminates such a bias in deterministic PG methods.

→ 10.01.2023: Our article has been accepted to the Journal of Artificial Intelligence Research. To our knowledge, this is the first study that addresses the poor empirical performance of the PER algorithm in actor-critic methods. Publication is on its way.

→ 06.27.2023: Our paper has been accepted to Machine Learning. It aims to adapt the self-determination theory into the reinforcement learning paradigm. Publication on the way.

→ 04.15.2023: I’ve accepted the offer from Yale University. Starting in Fall 2023, I’ll be pursuing my Ph.D. studies in the School of Arts & Sciences.

→ 04.11.2023: I’ve received a first-year Ph.D. fellowship from the University of California, San Diego.

→ 03.14.2023: Our paper has been accepted to the Workshop on Data Driven Intelligence @ IEEE International Conference on Communications (ICC) 2023. This is the first RL-based approach in the literature for the RIS configuration problem that accounts hardware impairments.

→ 11.05.2022: Our paper has been accepted to the prestigious Deep Reinforcement Learning Workshop @ NeurIPS 2022.

→ 09.02.2022: Inspired by the theories on animal psychological systems, our paper has been accepted to the IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning.

→ 06.13.2022: Our paper has been accepted to the Responsible Decision Making in Dynamic Environments workshop @ ICML 2022.

→ 03.21.2022: I’m awarded the 5G and Beyond Fellowship from Turk Telekom Technologies.

→ 09.10.2021: 3 papers have been accepted to IEEE 33rd International Conference on Tools with Artificial Intelligence (ICTAI). Start to my master’s.