Mert Yuksekgonul

I'm a third year PhD student in Computer Science at Stanford University. I am lucky to be advised by James Zou and Carlos Guestrin.

These days, my research is in the intersection between alignment and creativity. So far, I worked on making machine learning models more reliable, and their failures more predictable. This broad interest led me to work on topics around interpretability, robustness, multimodality, and uncertainty. I really enjoy thinking about abstraction, concepts, and compositionality in humans and machines.

During Summer 2023, I interned at MSR working with Besmira Nushi in the Adaptive Systems and Interaction Group .

I was extremely fortunate to have many wonderful mentors in my undergraduate years. I worked with Prof. Mackenzie Mathis, Prof. Alexander Mathis and Prof. Matthias Bethge as part of Bethge Lab(Tübingen/MPI) and Adaptive Motor Control Lab (Harvard/EPFL). My last undergrad research gig was with Dr. Xavier Boix as part of Poggio Lab(MIT) and Sinha Lab(MIT). I started Machine Learning research with Prof. Mustafa Baydogan at Bogazici University.

[ Email  /  Github  /  Twitter  /  Google Scholar ]

profile photo

Recent News

► Older News

Selected Publications

bow When and why vision-language models behave like bags-of-words, and what to do about it?
Mert Yuksekgonul, Federico Bianchi, Pratyusha Kalluri, Dan Jurafsky, James Zou
Oral @ ICLR 2023 (Top 5% of all accepted papers)
[ Paper , Code ]
▶ Show Description
beyond_confidence Beyond Confidence: Reliable Models Should Also Quantify Atypicality
Mert Yuksekgonul, Linjun Zhang, James Zou, Carlos Guestrin
NeurIPS 2023, Contributed Talk @ ICLR 2023 Workshop on Trustworthy Machine Learning
[Code Soon ]
▶ Show Description
attention_satisfies Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models
Mert Yuksekgonul, Varun Chandrasekaran, Erik Jones, Suriya Gunasekar, Ranjita Naik, Hamid Palangi , Ece Kamar , Besmira Nushi
ICLR 2024
[ Paper, Code ]
▶ Show Description
pcbm Post-hoc Concept Bottleneck Models
Mert Yuksekgonul, Maggie Wang, James Zou
Spotlight @ ICLR2023 (Top 25% of all accepted papers)
[ Paper, Code ]
▶ Show Description
plip Leveraging medical Twitter to build a visual–language foundation model for pathology AI
Zhi Huang*, Federico Bianchi*, Mert Yuksekgonul, Thomas Montine, James Zou
Nature Medicine
[ Preprint, Demo ]
▶ Show Description
cce Meaningfully debugging model mistakes using conceptual counterfactual explanations
Abubakar Abid*, Mert Yuksekgonul*, James Zou
ICML 2022
[ Paper , Code ]
▶ Show Description

► More Publications

Template from this website.