Profile

Kirill Bykov is a postdoctoral researcher in the Explainable Machine Learning Group at TUM and Helmholtz Munich, led by Prof. Zeynep Akata. He is broadly interested in Explainable AI and Mechanistic Interpretability for Computer Vision and Natural Language Processing, with a focus on developing principled methods to better understand and improve Deep Neural Networks.

Before his current position, Kirill defended his Ph.D. in Computer Science with summa cum laude honors at TU Berlin, under the supervision of Prof. Klaus-Robert Müller and Prof. Marina Höhne. His doctoral research centered on explainability in Deep Neural Networks, resulting in publications at top-tier venues such as NeurIPS, AAAI, and TMLR. During his Ph.D., he actively contributed to the academic community through invited talks, panel discussions, and the supervision of student projects that led to award-winning and NeurIPS-published work. Prior to his doctoral studies, Kirill earned a Master’s degree cum laude in Data Science and Engineering from TU Berlin and TU Eindhoven, and a Bachelor’s degree in Applied Mathematics and Computer Science from Saint Petersburg State University.