3 papers
cs.CV2025
Object-level Self-Distillation for Vision Pretraining
Çağlar Hızlı, Çağatay Yıldız, Pekka Marttinen
State-of-the-art vision pretraining methods rely on image-level self-distillation from object-centric datasets such as ImageNet, implicitly assuming each image contains a single ob…
cs.CL2025
From Raw Corpora to Domain Benchmarks: Automated Evaluation of LLM Domain Expertise
Nitin Sharma, Thomas Wolfers, Çağatay Yıldız
Accurate domain-specific benchmarking of LLMs is essential, specifically in domains with direct implications for humans, such as law, healthcare, and education. However, existing b…
cs.LG2023
Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization
Sebastian Dziadzio, Çağatay Yıldız, Gido M. van de Ven +3
The ability of machine learning systems to learn continually is hindered by catastrophic forgetting, the tendency of neural networks to overwrite previously acquired knowledge when…