This course will teach you the theory behind large language models (LLMs) and give you the tools to implement LLMs in your applications.

Contact

• Dr. Bruno Yun

  • Email: [email protected]
  • Website: https://bruno-yun.notion.site/
  • Office: Nautibus, 12.038 (second floor).
  • Working hours: 9:00 am to 5:00 pm

  Send your queries by email. For a face-to-face meeting, contact me by email to arrange one.

Structure of the course

This part of the course will have 18 hours of lectures, 12 hours of practicals.

The teaching timetable is split into three sessions as follows.

• Part 1: Zoom on the transformer architecture (9th of November 2026)

  The RNN architectures

  The Transformer model for NLG

  Continuous assessment 1 (written test, 30%) → Deadline 20/11/2026 23:59

• Part 2: A short history of large language models (20th of November 2026)

  A quick survey of existing LLMs

  Reducing the cost of running LLMs

• Part 3: Pre-training and Post-training (25th of November 2026)

  Pre-training

  Post-training/Fine-tuning

• Part 4: Practical techniques and tools for large language models (30th of November 2026)

  Prompt engineering

  Retrieval augmented generation (RAG) and context-engineering

  Useful tools for large language models

  Continuous assessment 2 (oral presentation, 30%) → Deadline 13th of December 2026 23:59

• Part 5: Evaluation and ethical questions of large language models (1st of December 2026)

  Evaluating LLMs

  Security, privacy, and ethical questions of LLM

• Part 6: Exciting research discussion on large language models (2nd of December 2026)

  • Choice of the following:

    DeepSeek-R1: Cheap large reasoning model with reinforcement learning

    Pros and Cons of selective state space models (SSMs)

    Test-time training (TTT) models

    Mixture-of-experts

    Mixture of Block Attention

    Large Language Models in 1.58 Bits?

    Looped Language Models

    Discrete Diffusion Modeling

• Part 7: Additional practical, support on project, and oral presentations (4th of December 2026)

  Continuous assessment 3 (code and report, 40%) → Deadline 13th of December 2026 23:59

Practicals 1 (10th, 20th, 24th of November 2026, 2 sessions)

Practical 0: Background on PyTorch

Practical 1: Tokenizers, embeddings, and multi-head attention from scratch

Practicals 2 (24th & 27th of November 2026, 2 sessions)