Samet Oymak

A look into how attention mechanisms enhance language processing in AI.

Exploring how transformers adapt to predict outputs in unknown systems.

A look into how transformers use attention layers for better language processing.

Examining Mamba's capabilities and its hybrid model with Transformers.

Introducing CAP to improve fairness and efficiency in machine learning models.

A new method enhances federated learning by addressing client differences.

TREACLE helps users select the best language models within budget and time limits.

A closer look at self-attention mechanisms in language processing models.

Study reveals insights into in-context learning performance across various model architectures.

Selective self-attention improves language understanding by focusing on key information.