Lil'Log
Lilian Weng's deep technical write-ups on machine learning.
- Harness Engineering for Self-ImprovementJuly 4, 2026
- Scaling Laws, CarefullyJune 24, 2026
- Why We ThinkMay 1, 2025
- Reward Hacking in Reinforcement LearningNovember 28, 2024
- Extrinsic Hallucinations in LLMsJuly 7, 2024
- Diffusion Models for Video GenerationApril 12, 2024
- Thinking about High-Quality Human DataFebruary 5, 2024
- Adversarial Attacks on LLMsOctober 25, 2023
- LLM Powered Autonomous AgentsJune 23, 2023
- Prompt EngineeringMarch 15, 2023
- The Transformer Family Version 2.0January 27, 2023
- Large Transformer Model Inference OptimizationJanuary 10, 2023
- Some Math behind Neural Tangent KernelSeptember 8, 2022
- Generalized Visual Language ModelsJune 9, 2022
- Learning with not Enough Data Part 3: Data GenerationApril 15, 2022
- Learning with not Enough Data Part 2: Active LearningFebruary 20, 2022
- Learning with not Enough Data Part 1: Semi-Supervised LearningDecember 5, 2021
- How to Train Really Large Models on Many GPUs?September 24, 2021
- What are Diffusion Models?July 11, 2021
- Contrastive Representation LearningMay 31, 2021