LLM Learning Journey¶

Welcome to my Large Language Models learning notes! This documentation site serves as a comprehensive collection of my personal insights, research notes, and explorations in the field of LLMs and AI.

About These Notes¶

These Markdown learning notes are a collection of my personal thoughts and insights gathered from various sources. The content may not be perfectly organized, as I take notes whenever I come across something interesting and use a "topic online clustering" approach to group them. This method allows me to capture ideas in real-time but may result in notes that are not in a strict order.

While these notes help me in my LLMs learning journey, they may not directly align with your needs or be as structured as you'd prefer. Feel free to explore topics that interest you!

Topics Covered¶

Core LLM Topics¶

• AI Agents - Frameworks, architectures, and implementations of AI agents
• RAG (Retrieval-Augmented Generation) - Best practices and workflows for RAG systems
• Reinforcement Learning & Fine-Tuning - RLHF, alignment, and fine-tuning techniques
• Prompt Engineering - Crafting effective prompts for LLMs

Evaluation & Optimization¶

• Evaluation - Metrics, benchmarks, and evaluation methodologies
• Model Compression - Quantization, pruning, and distillation techniques

Specialized Topics¶

• Recommendation Systems - LLMs in recommendation systems
• Miscellaneous - Other interesting topics and findings

Talks & Seminars¶

Conference notes from talks, tutorials, panels, and workshops:

• NeurIPS 2025 - AI evaluation, reasoning models, explainability, coding agents, and responsible AI

Online Courses¶

I've also documented notes from various online courses:

• GenAI 5-Day Course with Google
• Hugging Face AI Agent Course

Navigation Tips¶

• Use the search bar at the top to find specific topics or keywords
• Browse by topic sections in the left sidebar
• Check the table of contents on the right for quick navigation within pages
• Look for tags to find related content across different topics

Contributing & Feedback¶

These are personal learning notes, but if you find errors or have suggestions, feel free to open an issue or PR on GitHub!

Happy learning!