Skip to content

Topics Overview

This section contains detailed notes and research on various topics related to Large Language Models and AI.

Major Topics

AI Agents

Learn about AI agent frameworks like AutoGen, CrewAI, and LangGraph. Includes paper reviews on LAMBDA, TaskWeaver, and more.

RAG (Retrieval-Augmented Generation)

Comprehensive guide to RAG workflows, best practices, chunking strategies, and Graph RAG implementations.

Reinforcement Learning & Fine-Tuning

Deep dive into RLHF (Reinforcement Learning from Human Feedback), alignment techniques, and the LIMA paper on efficient fine-tuning.

Prompt Engineering

Principles and best practices for crafting effective prompts, including structure, clarity, and complex task handling.

Evaluation & Optimization

Evaluation

LLM evaluation methods, metrics (BLEU, ROUGE, perplexity), and benchmarks (GLUE, MMLU, BigBench, etc.).

Model Compression

Techniques for model compression including quantization (PTQ, QAT), pruning, and knowledge distillation.

Specialized Areas

Recommendation Systems

How generative models enhance recommendation systems.

Miscellaneous

Other interesting topics including LLM fundamentals and hallucination phenomena.

Browse by Content Type

  • Overview & Frameworks: AI-Agent, Prompt, Evaluation
  • Paper Reviews: AI-Agent, RAG, RFT
  • Implementation Guides: RAG, Model Compression
  • Research Notes: All topics