NLP Course, 2026

Current curriculum covers topic from basic NLP techinques to the most modern ones, that may be helpful for custom training of LLMs:

• NLP Basics: tokenization, text preprocessing, text representations
• Text & Language Models: embeddings, n-gram models, RNNs, LSTMs, seq2seq, attention
• Transformers & LLMs: Transformer, pre-training (MLM/CLM), prompting, fine-tuning, PEFT
• Scaling & Optimization: : distributed training, MoE, efficient inference, quantization
• Retrieval & Agents: Information Retrieval, RAG, agent-based systems
• Post-training: alignment, RLHF, DPO

Course Staff

• German Gritsai @grgera
• Anastasiia Vozniuk @natriistorm
• Ildar Khabutdinov @depinwhite

Materials

Week #	Date	Topic	Lecture	Seminar	Recording
1	February 10	Intro to NLP	slides, slides with notes	ipynb	record

Homeworks

TBA

Game Rules

TBA

Final Grade:

TBA

Prerequisities

• Probability Theory + Statistics
• Machine Learning
• Python
• Basic knowledge on NLP

We expect students to know basics of Natural Language Processing, as the course focuses on more advanced topics. When you unsure about the basics, we recommned to watch these lectures / read these materials:

1. Course from Lena Voita