Sunwoo Bae

I am an undergraduate student at KAIST, currently interning at the COCO Lab under the supervision of Hyunwoo Kim.

My research focuses on understanding and advancing reasoning capabilities in Large Language Models. I investigate how the entire training pipeline-encompassing strategic data synthesis, algorithmic design (specifically Reinforcement Learning), and architectural choices-shapes reasoning behaviors in both pre-training and post-training stages.

I am particularly interested in structured reasoning and socially grounded intelligence, aiming to develop models that demonstrate robust generalization and reliable reasoning beyond superficial pattern matching.