Syllabus

Date	Topics	Video from playlist
September 26^th, 2025	Lecture 1: Transformer [slides] [panopto] • Background on NLP and tasks • Tokenization • Embeddings • Word2vec, RNN, LSTM • Attention mechanism • Transformer architecture	1:41:58
October 3^rd, 2025	Lecture 2: Transformer-based models & tricks [slides] [panopto] • Attention approximation • MHA, MQA, GQA • Position embeddings (regular, learned) • RoPE and applications • Transformer-based architectures • BERT and its derivatives	1:47:19
October 10^th, 2025	Lecture 3: Large Language Models [slides] [panopto] • Definition and architecture • Mixture of experts • Context length, temperature • Sampling strategies • Prompting, in-context learning • Chain of thought • Self-consistency	1:48:44
October 17^th, 2025	Lecture 4: LLM training [slides] [panopto] • Pretraining • Quantization • Hardware optimization • Supervised finetuning (SFT) • Parameter-efficient finetuning (LoRA)	1:47:27
October 24^th, 2025	Midterm [exam] [solutions]
October 31^st, 2025	Lecture 5: LLM tuning [slides] [panopto] • Preference tuning • RLHF overview • Reward modeling • RL approaches (PPO and variants) • DPO	1:47:42
November 7^th, 2025	Lecture 6: LLM reasoning [slides] [panopto] • Reasoning models • RL for reasoning • GRPO • Scaling	1:47:10
November 14^th, 2025	Lecture 7: Agentic LLMs [slides] [panopto] • Retrieval-augmented generation • Advanced RAG techniques • Function calling • Agents • ReAct framework	1:49:23
November 21^st, 2025	Lecture 8: LLM evaluation [slides] [panopto] • LLM-as-a-judge overview • Best practices and benefits • Biases and pitfalls	1:49:25
December 5^th, 2025	Lecture 9: Current trends [slides] [panopto] • Recap • Trending topics • Closing thoughts	1:51:31
December 10^th, 2025	Final