The Curious Engineer

All blogs / AI / ML

Lil'Log

lilianweng.github.io

Document my learning notes.

AI / ML

’05’10’15’20’25
Posts
53 from 1 Jan 2001 to 4 Jul 2026
Posting
now and then (2 in the last year)
Kind
personal blog
Feed
https://lilianweng.github.io/index.xml

2026 2

  1. Harness Engineering for Self-Improvement
  2. Scaling Laws, Carefully

2025 1

  1. Why We Think

2024 4

  1. Reward Hacking in Reinforcement Learning
  2. Extrinsic Hallucinations in LLMs
  3. Diffusion Models for Video Generation
  4. Thinking about High-Quality Human Data

2023 5

  1. Adversarial Attacks on LLMs
  2. LLM Powered Autonomous Agents
  3. Prompt Engineering
  4. The Transformer Family Version 2.0
  5. Large Transformer Model Inference Optimization

2022 4

  1. Some Math behind Neural Tangent Kernel
  2. Generalized Visual Language Models
  3. Learning with not Enough Data Part 3: Data Generation
  4. Learning with not Enough Data Part 2: Active Learning

2021 6

  1. Learning with not Enough Data Part 1: Semi-Supervised Learning
  2. How to Train Really Large Models on Many GPUs?
  3. What are Diffusion Models?
  4. Contrastive Representation Learning
  5. Reducing Toxicity in Language Models
  6. Controllable Neural Text Generation

2020 5

  1. How to Build an Open-Domain Question Answering System?
  2. Neural Architecture Search
  3. Exploration Strategies in Deep Reinforcement Learning
  4. The Transformer Family
  5. Curriculum for Reinforcement Learning

2019 6

  1. Self-Supervised Representation Learning
  2. Evolution Strategies
  3. Meta Reinforcement Learning
  4. Domain Randomization for Sim2Real Transfer
  5. Are Deep Neural Networks Dramatically Overfitted?
  6. Generalized Language Models

2018 9

  1. Object Detection Part 4: Fast Detection Models
  2. Meta-Learning: Learning to Learn Fast
  3. Flow-based Deep Generative Models
  4. From Autoencoder to Beta-VAE
  5. Attention? Attention!
  6. Implementing Deep Reinforcement Learning Models with Tensorflow + OpenAI Gym
  7. Policy Gradient Algorithms
  8. A (Long) Peek into Reinforcement Learning
  9. The Multi-Armed Bandit Problem and Its Solutions

2017 10

  1. Object Detection for Dummies Part 3: R-CNN Family
  2. Object Detection for Dummies Part 2: CNN, DPM and Overfeat
  3. Object Detection for Dummies Part 1: Gradient Vector, HOG, and SS
  4. Learning Word Embedding
  5. Anatomize Deep Learning with Information Theory
  6. From GAN to WGAN
  7. How to Explain the Prediction of a Machine Learning Model?
  8. Predict Stock Prices Using RNN: Part 2
  9. Predict Stock Prices Using RNN: Part 1
  10. An Overview of Deep Learning for Curious People

2001 1

  1. Faq