My research currently focused on the intersection of visual grounding and leveraging multimodal models to reason about the real-world as an agent. My long-term goal is to develop robot-learning paradigms in real-world problems by enhancing visual reasoning and grounding objects with language understandings.
I am pursuing my Master's Degree at Grauduate School of Artificial Intelligence in Seoul National University. I received my Bachelor's Degree from Sogang Unviersity.
Go to the project directory and run bundle exec jekyll serve
kyuhwan.shim (at) snu (dot) ac (dot) kr