Chiyoung Kim

Chiyoung Kim is a graduate student in AI at Chung-Ang University (CAU) in Seoul, South Korea, and is also affiliated with Ulsan National Institute of Science and Technology (UNIST). He is a co-author of CoTinyVLA, a sub-billion-parameter Vision-Language-Action model that uses chain-of-thought distillation and structured supervision to achieve robustness on the LIBERO-Plus benchmark while fitting within embedded robotic memory budgets. His research focuses on efficient VLA model design, including pruning and distillation techniques for robot action generation.