56,966 blogs · [ { "id": "01a07d5d-7d38-7341-b60d-41c4df0aa2c6", "title": "Harness Engineering for Self-Improvement", "url": "https://lilianweng.github.io/posts/2026-07-04-harness/", "published_at": "2026-07-04T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4df5c7417", "title": "Scaling Laws, Carefully", "url": "https://lilianweng.github.io/posts/2026-06-24-scaling-laws/", "published_at": "2026-06-24T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e01d6478", "title": "Why We Think", "url": "https://lilianweng.github.io/posts/2025-05-01-thinking/", "published_at": "2025-05-01T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e0c3c086", "title": "Reward Hacking in Reinforcement Learning", "url": "https://lilianweng.github.io/posts/2024-11-28-reward-hacking/", "published_at": "2024-11-28T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e17b955c", "title": "Extrinsic Hallucinations in LLMs", "url": "https://lilianweng.github.io/posts/2024-07-07-hallucination/", "published_at": "2024-07-07T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e266ad94", "title": "Diffusion Models for Video Generation", "url": "https://lilianweng.github.io/posts/2024-04-12-diffusion-video/", "published_at": "2024-04-12T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e2af69ce", "title": "Thinking about High-Quality Human Data", "url": "https://lilianweng.github.io/posts/2024-02-05-human-data-quality/", "published_at": "2024-02-05T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e2c1db3a", "title": "Adversarial Attacks on LLMs", "url": "https://lilianweng.github.io/posts/2023-10-25-adv-attack-llm/", "published_at": "2023-10-25T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e331359b", "title": "LLM Powered Autonomous Agents", "url": "https://lilianweng.github.io/posts/2023-06-23-agent/", "published_at": "2023-06-23T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e35a2d3e", "title": "Prompt Engineering", "url": "https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/", "published_at": "2023-03-15T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e40597f4", "title": "The Transformer Family Version 2.0", "url": "https://lilianweng.github.io/posts/2023-01-27-the-transformer-family-v2/", "published_at": "2023-01-27T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e433fb85", "title": "Large Transformer Model Inference Optimization", "url": "https://lilianweng.github.io/posts/2023-01-10-inference-optimization/", "published_at": "2023-01-10T17:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e52d354a", "title": "Some Math behind Neural Tangent Kernel", "url": "https://lilianweng.github.io/posts/2022-09-08-ntk/", "published_at": "2022-09-08T17:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e5893b8c", "title": "Generalized Visual Language Models", "url": "https://lilianweng.github.io/posts/2022-06-09-vlm/", "published_at": "2022-06-09T22:10:30+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e5b46774", "title": "Learning with not Enough Data Part 3: Data Generation", "url": "https://lilianweng.github.io/posts/2022-04-15-data-gen/", "published_at": "2022-04-15T22:10:30+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e611aba4", "title": "Learning with not Enough Data Part 2: Active Learning", "url": "https://lilianweng.github.io/posts/2022-02-20-active-learning/", "published_at": "2022-02-20T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e665f98f", "title": "Learning with not Enough Data Part 1: Semi-Supervised Learning", "url": "https://lilianweng.github.io/posts/2021-12-05-semi-supervised/", "published_at": "2021-12-05T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e73dd0e2", "title": "How to Train Really Large Models on Many GPUs?", "url": "https://lilianweng.github.io/posts/2021-09-25-train-large/", "published_at": "2021-09-24T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e8141a98", "title": "What are Diffusion Models?", "url": "https://lilianweng.github.io/posts/2021-07-11-diffusion-models/", "published_at": "2021-07-11T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e8997316", "title": "Contrastive Representation Learning", "url": "https://lilianweng.github.io/posts/2021-05-31-contrastive/", "published_at": "2021-05-31T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e96f7181", "title": "Reducing Toxicity in Language Models", "url": "https://lilianweng.github.io/posts/2021-03-21-lm-toxicity/", "published_at": "2021-03-21T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4e9ef7de5", "title": "Controllable Neural Text Generation", "url": "https://lilianweng.github.io/posts/2021-01-02-controllable-text-generation/", "published_at": "2021-01-02T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4ea5af004", "title": "How to Build an Open-Domain Question Answering System?", "url": "https://lilianweng.github.io/posts/2020-10-29-odqa/", "published_at": "2020-10-29T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4eac34d52", "title": "Neural Architecture Search", "url": "https://lilianweng.github.io/posts/2020-08-06-nas/", "published_at": "2020-08-06T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4eba92d09", "title": "Exploration Strategies in Deep Reinforcement Learning", "url": "https://lilianweng.github.io/posts/2020-06-07-exploration-drl/", "published_at": "2020-06-07T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4ebfa24d2", "title": "The Transformer Family", "url": "https://lilianweng.github.io/posts/2020-04-07-the-transformer-family/", "published_at": "2020-04-07T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4eca359dd", "title": "Curriculum for Reinforcement Learning", "url": "https://lilianweng.github.io/posts/2020-01-29-curriculum-rl/", "published_at": "2020-01-29T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4ecdcc89d", "title": "Self-Supervised Representation Learning", "url": "https://lilianweng.github.io/posts/2019-11-10-self-supervised/", "published_at": "2019-11-10T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4ed002101", "title": "Evolution Strategies", "url": "https://lilianweng.github.io/posts/2019-09-05-evolution-strategies/", "published_at": "2019-09-05T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4ed8b7826", "title": "Meta Reinforcement Learning", "url": "https://lilianweng.github.io/posts/2019-06-23-meta-rl/", "published_at": "2019-06-23T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4eda00d9f", "title": "Domain Randomization for Sim2Real Transfer", "url": "https://lilianweng.github.io/posts/2019-05-05-domain-randomization/", "published_at": "2019-05-05T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4ee0489b1", "title": "Are Deep Neural Networks Dramatically Overfitted?", "url": "https://lilianweng.github.io/posts/2019-03-14-overfit/", "published_at": "2019-03-14T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4eea7e7d1", "title": "Generalized Language Models", "url": "https://lilianweng.github.io/posts/2019-01-31-lm/", "published_at": "2019-01-31T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4ef328bf2", "title": "Object Detection Part 4: Fast Detection Models", "url": "https://lilianweng.github.io/posts/2018-12-27-object-recognition-part-4/", "published_at": "2018-12-27T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4ef9bf228", "title": "Meta-Learning: Learning to Learn Fast", "url": "https://lilianweng.github.io/posts/2018-11-30-meta-learning/", "published_at": "2018-11-30T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f01f9916", "title": "Flow-based Deep Generative Models", "url": "https://lilianweng.github.io/posts/2018-10-13-flow-models/", "published_at": "2018-10-13T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f0d363da", "title": "From Autoencoder to Beta-VAE", "url": "https://lilianweng.github.io/posts/2018-08-12-vae/", "published_at": "2018-08-12T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f1776033", "title": "Attention? Attention!", "url": "https://lilianweng.github.io/posts/2018-06-24-attention/", "published_at": "2018-06-24T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f1cdb746", "title": "Implementing Deep Reinforcement Learning Models with Tensorflow + OpenAI Gym", "url": "https://lilianweng.github.io/posts/2018-05-05-drl-implementation/", "published_at": "2018-05-05T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f1e735f7", "title": "Policy Gradient Algorithms", "url": "https://lilianweng.github.io/posts/2018-04-08-policy-gradient/", "published_at": "2018-04-08T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f2ccc9a7", "title": "A (Long) Peek into Reinforcement Learning", "url": "https://lilianweng.github.io/posts/2018-02-19-rl-overview/", "published_at": "2018-02-19T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f3c438c9", "title": "The Multi-Armed Bandit Problem and Its Solutions", "url": "https://lilianweng.github.io/posts/2018-01-23-multi-armed-bandit/", "published_at": "2018-01-23T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f4311e03", "title": "Object Detection for Dummies Part 3: R-CNN Family", "url": "https://lilianweng.github.io/posts/2017-12-31-object-recognition-part-3/", "published_at": "2017-12-31T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f4ba91d1", "title": "Object Detection for Dummies Part 2: CNN, DPM and Overfeat", "url": "https://lilianweng.github.io/posts/2017-12-15-object-recognition-part-2/", "published_at": "2017-12-15T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f4ebdd11", "title": "Object Detection for Dummies Part 1: Gradient Vector, HOG, and SS", "url": "https://lilianweng.github.io/posts/2017-10-29-object-recognition-part-1/", "published_at": "2017-10-29T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f58e5a34", "title": "Learning Word Embedding", "url": "https://lilianweng.github.io/posts/2017-10-15-word-embedding/", "published_at": "2017-10-15T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f5ece3da", "title": "Anatomize Deep Learning with Information Theory", "url": "https://lilianweng.github.io/posts/2017-09-28-information-bottleneck/", "published_at": "2017-09-28T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f60f44d8", "title": "From GAN to WGAN", "url": "https://lilianweng.github.io/posts/2017-08-20-gan/", "published_at": "2017-08-20T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f6b01f41", "title": "How to Explain the Prediction of a Machine Learning Model?", "url": "https://lilianweng.github.io/posts/2017-08-01-interpretation/", "published_at": "2017-08-01T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f7715797", "title": "Predict Stock Prices Using RNN: Part 2", "url": "https://lilianweng.github.io/posts/2017-07-22-stock-rnn-part-2/", "published_at": "2017-07-22T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f7b7e585", "title": "Predict Stock Prices Using RNN: Part 1", "url": "https://lilianweng.github.io/posts/2017-07-08-stock-rnn-part-1/", "published_at": "2017-07-08T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f83b0056", "title": "An Overview of Deep Learning for Curious People", "url": "https://lilianweng.github.io/posts/2017-06-21-overview/", "published_at": "2017-06-21T00:00:00+00:00" }, { "id": "01a07d5d-7d38-7341-b60d-41c4f91ceaf7", "title": "FAQ", "url": "https://lilianweng.github.io/faq/", "published_at": null } ] posts Claim your blog
Back to Lilian Weng
Blog · corpus.blog/blogs/lilianweng.github.io/posts

Lilian Weng

lilianweng.github.io

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

Undated