Talk is Cheap, Show me code - Linus Torvalds
Persistence is the true gift, 꾸준함이 재능이다
공부는 “대칭화” → “모듈화” → “순서화” 후에 자동생성 되고 확장된다.
Hello, I’m Yoojin Shin. This blog's notes are to keep track of my progress and record my self-teaching of programming and math problems as a CS major student. I finish my undergraduate at the University of Utah in Psychology, and Communication and my Master of Science in Computer Science (Data Science) at Hanyang University, Seoul. Following my curiosity about how people’s cognition changes during interaction, the interaction here means any communication between humans to humans and humans to AIs -, I’m highly interested in how language impacts our cognition and how the process of learning progresses inside the human brain. I believe the human brain not only takes in information solely from texts, but also from audio and images, detecting subtle changes in tone and pitch in human voices, as well as subtle changes in facial expressions and gestures. I am highly interested in implementing human-like reasoning AI that naturally interacts with people. To implement such tasks, a language-based Large Multimodal Model (that integrates vision/audio/text) is necessary, which is my main research interest. To solve the problem, modal synchronization, which is affected by different alignment needs to be addressed.