Recent Advances in Deep Learning (AI602, Fall 2026)

Deep learning is a new area of machine learning research, which have demonstrated states-of-the-art performance on many artificial intelligence tasks, e.g., computer vision, speech recognition and natural language processing. In this lecture, I will cover some of recent advances in this area, in particular, under perspective of foundation models.

Announcement

• The maximum number of course registrations is around 60, and we cannot accept more now (do not send an email to Instructor or TA).

Schedule

• Course introduction: Introduction to AI602

• Lecture 0: Overview of recent foundation models

• Lecture 1: Neural architectures for LLM

• Lecture 2: Training recipe for LLM (pre-training, post-training)

• Lecture 3: LLM inference & test-time compute

• Lecture 4: LLM agents (e.g., coding agents)

• Lecture 5: Multi-modal models (including LVM, video diffusion)

• Lecture 6: Vision-language-action and world models

• Lecture 7: LVM agents for robotics

Contact

Instructor: Jinwoo Shin (jinwoos@kaist.ac.kr)
TA: Byungjun Yoon (byungjuny@kaist.ac.kr), Suhyeok Jang (jasuhe900@kaist.ac.kr)