Profile

Merve Tapli is a visiting researcher in the Explainable Machine Learning group, supervised by Prof. Zeynep Akata. She received her Bachelor's and Master's degrees from Middle East Technical University in Ankara, where she is currently pursuing her PhD under the supervision of Assoc. Prof. Emre Akbas. Her primary research interest is interpretable computer vision, with a focus on concept bottleneck models — making image classifiers ground their predictions in human-understandable concepts without sacrificing accuracy.

Publications

"Rethinking Concept Bottleneck Models: From Pitfalls to Solutions"
Merve Tapli, Quentin Bouniot, Wolfgang Stammer, Zeynep Akata, Emre Akbas
CVPR 2026

"Caption Bottleneck Models"
Seref Baris Cagliyan, Umut Ozdemir, Merve Tapli, Emre Akbas
ECCV 2026