Getting Ready for the Workshop

Curated materials to help you prepare and get the most out of your workshop experience

Welcome! We've carefully selected a collection of high-quality learning materials to help you prepare for the SCIPE Workshop on LLMs. Whether you're new to the field or looking to deepen your understanding, these resources will provide a solid foundation for the workshop.

Take your time exploring these materials at your own pace. You don't need to complete everything before the workshop, but familiarizing yourself with the basics will help you get more value from the hands-on sessions.

Filter by Difficulty Level

Introduction to LLMs & Tutorials

Start here to build a strong foundation in LLMs

Beginner

How I Use LLMs

Andrej Karpathy

Practical insights on leveraging LLMs in real-world workflows. Learn how an expert integrates these tools into daily work and discovers what's possible with current technology.

Watch Video
Beginner

Large Language Models and Chatbots

IBM Technology

A comprehensive playlist that covers LLM fundamentals and chatbot development. These videos break down complex topics into digestible segments, perfect for building understanding step by step.

View Playlist
Intermediate

Let's Reproduce GPT-2 (124M)

Andrej Karpathy

An in-depth walkthrough of implementing GPT-2 from scratch. This is for those who want to understand the intricate details of transformer architecture and training. Highly rewarding for research-oriented participants.

Watch Video
Beginner

Learn RAG From Scratch

LangChain

Python AI tutorial on building retrieval-augmented generation systems. This practical guide shows you how to enhance LLMs with external knowledge, a technique we'll explore in the workshop.

Watch Tutorial
Beginner

Neural Networks

3Blue1Brown

Beautiful visual explanations of neural network concepts. If you're looking to understand the mathematical foundations with intuitive animations, this series is unmatched. Essential for grasping how neural networks actually work.

View Playlist

Generative AI & Language Models Courses

Comprehensive university courses on LLMs and transformers

Beginner

Transformers & Large Language Models (CME 295)

Stanford University, 2025

A comprehensive course dedicated to transformer architectures and large language models. Covers both theoretical foundations and practical implementations, ideal for understanding the complete picture of modern LLMs.

View Playlist | Course Page
Intermediate

Language Modeling from Scratch (CS336)

Stanford University, 2025

Build language models from the ground up. This course provides deep understanding of how transformers and language models work at a fundamental level.

View Playlist | Course Page
Intermediate

Deep Reinforcement Learning (CS224R)

Stanford University, 2025

Explore deep reinforcement learning techniques that are increasingly important for training and fine-tuning LLMs with human feedback.

First Lecture | Course Page
Advanced

Advanced Natural Language Processing (CS11-747)

Carnegie Mellon University, Fall 2025

Dive deeper into NLP with this advanced course. Features video lectures covering cutting-edge topics in natural language processing. Great for those who want to explore beyond the basics.

View Playlist | Course Page
Advanced

Inference Algorithms for Language Modeling (11-664/763)

Carnegie Mellon University, Fall 2025

Focused course on inference optimization techniques and test-time scaling. Perfect for understanding how to make LLMs faster and more efficient, a topic we'll cover extensively in the workshop.

First Lecture | Course Page
Intermediate

Deep Learning (CS230)

Stanford University, Fall 2025

Build a strong foundation in deep learning concepts and applications. This course covers the fundamentals that underpin all modern LLMs. Recommended if you're new to deep learning.

First Lecture | Course Page
Advanced

A Practical Introduction to Diffusion Models (6.S183)

MIT, IAP 2025

Explore diffusion models, another important class of generative AI models. Understanding these techniques provides broader context for generative AI beyond language models.

View Playlist | Course Page
Advanced

An Introduction to Flow and Diffusion Models (6.S184)

MIT, IAP 2025

Deep dive into flow and diffusion models with mathematical foundations. Advanced course for those interested in the theoretical aspects of generative models.

View Playlist | Course Page

Background & Foundations

Mathematical foundations for understanding LLMs

Linear Algebra

Beginner

Essence of Linear Algebra

3Blue1Brown

Intuitive visual explanations of linear algebra concepts. Perfect for understanding the mathematical foundations behind neural networks and transformers.

View Playlist
Beginner

Linear Algebra (18.06)

MIT OpenCourseWare

Comprehensive introduction to linear algebra from MIT. Covers vectors, matrices, eigenvalues, and more - all essential for understanding deep learning.

View Playlist | Course Page
Intermediate

Matrix Methods in Data Analysis, Signal Processing, and Machine Learning (18.065)

MIT

Advanced matrix methods with direct applications to machine learning. Covers singular value decomposition, principal component analysis, and optimization techniques.

View Playlist | Course Page

Calculus

Beginner

Essence of Calculus

3Blue1Brown

Visual intuition for calculus concepts. Essential for understanding gradients, derivatives, and the optimization algorithms used in training neural networks.

View Playlist
Intermediate

Matrix Calculus for Machine Learning and Beyond

MIT, IAP 2023

Specialized course on matrix calculus with focus on machine learning applications. Covers gradients, Jacobians, and automatic differentiation.

View Playlist | Course Page

Probability & Statistics

Beginner

Probability for Computer Scientists (CS109)

Stanford University

Essential probability concepts for computer science and machine learning. Covers distributions, random variables, and statistical inference.

View Playlist | Course Page
Beginner

Statistics 110: Probability

Harvard University

Comprehensive introduction to probability theory. In-depth coverage of probability concepts with clear explanations and examples.

View Playlist | Course Page

How to Prepare

For Beginners

Priority: Start with Andrej Karpathy's 1-hour introduction, then watch the 3Blue1Brown neural networks series. These two resources will give you a solid conceptual foundation.

Optional: Browse the IBM Technology playlist for specific topics that interest you.

For Practitioners

Priority: Review "How I Use LLMs" and the RAG tutorial to see practical applications. Look at the Stanford CME 295 syllabus to identify areas where you want to deepen your knowledge.

Optional: Explore the inference optimization course if you're interested in deployment efficiency.

For Researchers

Priority: Review the advanced NLP course and inference algorithms course. Consider watching the GPT-2 reproduction video to understand implementation details.

Optional: Dive into the CS 230 materials if you want to refresh your deep learning fundamentals.

Timeline Suggestion

6+ weeks before: Start with the foundational videos and courses that interest you most.

2-4 weeks before: Focus on areas relevant to your goals (practitioner tools or research topics).

1 week before: Review key concepts and make sure you have your development environment set up.

Remember: These are suggestions to enhance your workshop experience, not requirements. Come with curiosity and a willingness to learn!

Ready to Join Us?

Registration is open from November 13 to December 25, 2025

Register for the Workshop

← Back to Workshop Home