Large Language Models Course

인하대학교 · 2026년 봄학기

본 강의는 대규모 언어 모델(Large Language Model; LLM)의 전반을 이해하는 것을 목표로 합니다. Transformer 및 LLM의 아키텍쳐부터 LLM의 학습과 인퍼런스, GPU 시스템 및 RL 기반 post-training까지 LLM을 이해하는 데 필요한 주요 내용을 학습합니다.
참고: 인하대학교에서 개설된 공식 강의명은 Multimodal VLM (ECE7115)이지만, 실제 강의 내용은 LLM을 중심으로 구성되어 있습니다.
강의자: 안남혁 (인하대학교 전기전자공학부)

강의 스케쥴 & 자료

날짜	내용	Slides	YouTube
3/2	No class (National holiday)
3/9	No class
3/16	Week 1. Introduction + Transformer - Course introduction - Resource accounting - Transformer	0. Course Introduction 1. Resource accounting 2. Transformer	1. Course Introduction + Resource accounting 2. Transformer
3/23	Week 2. LLM Basics - Pre-training - Post-training - Fine-tuning, Prompting	3. LLM Basics	3-1. LLM Basics (1) 3-2. LLM Basics (2)
3/30	Week 3. LLM Architecture (1) - Modern LLM models - Attention variants	4. Modern LLM Architecture	4-1. Modern LLM Architecture 4-2. Attention Variants
4/6	Week 4. LLM Architecture (2) - Mixture-of-experts - Scaling Laws	5. Mixture-of-Experts 6. Scaling Laws	5. Mixture-of-Experts 6. Scaling Laws
4/13	No class
4/20	Week 5. LLM Case Study - Recent model architectures	7. LLM Case Study	7. LLM Case Study
4/27	Week 6. Understanding GPUs - GPUs - FlashAttention	8. Understanding GPUs	8. Understanding GPUs & FlashAttention
5/4	Week 7. Parallelism - Multi-GPU/machine training	9. Parallelism	9. Parallelism
5/11	Week 8. Inference, Evaluation - Inference cost & techniques - Evaluation metrics	10. Inference 11. Evaluation	10. Inference 11. Evaluation
5/18	Week 9. Dataset, SFT - Training dataset - Supervised fine-tuning	12. Dataset & SFT	12. Dataset & SFT
5/25	No Class (National Holiday)
6/1	Week 10. RLHF - Introduction to RL - RL from human feedback	13. RLHF	13. RLHF
6/8	Week 11. Reasoning - Reasoning without Training - Training reasoning (RLVR)	14. Reasoning	14. Reasoning
6/15	Week 12. Modern Post-Training - Modern approach - Case study - Agentic systems