Mehran Kazemi

Learn how to simplify complex tasks into manageable steps for improved efficiency.

Improving language model adaptability through selective example retrieval.

Exploring how transformers tackle various graph reasoning tasks effectively.

A new data set assesses how LLMs reason with multiple images.

A new benchmark assesses how well models understand time and events.

Gemma 2 offers high performance in a compact size for language tasks.

Study reveals cheaper models may produce better training data for reasoning tasks.

Michelangelo evaluates language models on their ability to reason through long contexts.