Semih Yagcioglu — accepted AI-conference papers

2024

Sequential Compositional Generalization in Multimodal Models

Semih Yagcioglu, Osman Batur İnce, Aykut Erdem, Erkut Erdem, Desmond Elliott, Deniz Yuret

NAACL 2024long

The rise of large-scale multimodal models has paved the pathway for groundbreaking advances in generative modeling and reasoning, unlocking transformative applications in a variety of complex tasks. However, a pressing question that remains is their genuine capability for stronger forms of generaliz…

Cited by 1 Source ↗PDF ↗Scholar ↗

2023

Harnessing Dataset Cartography for Improved Compositional Generalization in Transformers

Osman Batur İnce, Tanin Zeraati, Semih Yagcioglu, Yadollah Yaghoobzadeh, Erkut Erdem, Aykut Erdem

EMNLP 2023long findings

Neural networks have revolutionized language modeling and excelled in various downstream tasks. However, the extent to which these models achieve compositional generalization comparable to human cognitive abilities remains a topic of debate. While existing approaches in the field have mainly focused…

Cited by 0 Source ↗code ↗Scholar ↗