Publications

Oğuz Kaan Yüksel, Etienne Boursier, Nicolas Flammarion (2023). First-order ANIL learns linear representations despite misspecified latent dimension.

PDF Cite

Oğuz Kaan Yüksel, Enis Simsar, Ezgi Gülperi Er, Pınar Yanardağ (2021). LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions. ICCV.

PDF Cite Code Project Video

Oğuz Kaan Yüksel, Sebastian U. Stich, Martin Jaggi, Tatjana Chavdarova (2021). Semantic Perturbations with Normalizing Flows for Improved Generalization. ICCV.

PDF Cite Code Video

Oğuz Kaan Yüksel, Sebastian U. Stich, Martin Jaggi, Tatjana Chavdarova (2021). Semantic Perturbations with Normalizing Flows for Improved Generalization. INNF+ Workshop, ICML.

PDF Cite Code

David Mizrahi, Oğuz Kaan Yüksel, Aiday Marlen Kyzy (2021). [Re] Can gradient clipping mitigate label noise?. ReScience C.

PDF Cite Code

Oğuz Kaan Yüksel, İnci Meliha Baytaş (2020). Adversarial Training with Orthogonal Regularization. SIU.

PDF Cite