1. Introduction
  3. Natural Language Processing
  4. LLMs
    1. Architecture
      1. FeedForward
      2. Attention
      3. Transformer
      4. Mixture of Experts
      5. Encoders
      6. Decoders
      7. Encoder-Decoder
      8. Multi-Latent Attention
    3. Prompting
      1. Prompt Engineering
      2. In-Context Learning
      3. Few-Shot Learning
      4. Chain of Thought
      5. Tree of Thought
      6. Soft prompts
      7. Hard prompts
    5. Fine-tuning
      1. Supervised Fine-Tuning
      2. RLHF
      3. DPO
      4. GRPO
      5. PEFT
      6. LoRA
      7. QLoRA
      8. DoRA
      9. YaRN
    7. Agents
      1. Tool Use
      2. Reflection
      3. Multi Agent
      4. Planning
    9. RAG
      1. Chunks
      2. Sliding Window
      3. Graph RAG
    11. Model Compression
      1. Distillation
      2. Quantization
    13. Efficient Inference
      1. Fast Attention
      2. KV Cache
    15. Decoding
      1. Multi-Token Prediction
      2. Top-k
      3. Greedy
      4. Speculative
    17. Miscellaneous
      1. Rejection Sampling
      2. Emergent
      3. LLM As Judge
  6. Notable Models
    1. BERT
    2. Llama-3
    3. DeepSeek-R1
    4. DeepSeek-v3
    5. Qwen2.5
  9. Evaluation
  10. Metrics
    1. Rouge
    2. Bleu
    3. pass@k