Lil'Log lilianweng.github.io

Why We Think

lilianweng.github.io·54w·Hacker News, Hacker News

Reward Hacking in Reinforcement Learning

lilianweng.github.io·75w·Hacker News

Extrinsic Hallucinations in LLMs

lilianweng.github.io·78w·Hacker News

Diffusion Models for Video Generation

lilianweng.github.io·72w·Hacker News

Thinking about High-Quality Human Data

lilianweng.github.io·118w

Adversarial Attacks on LLMs

lilianweng.github.io·133w

LLM Powered Autonomous Agents

lilianweng.github.io·150w

Prompt Engineering

lilianweng.github.io·165w

The Transformer Family Version 2.0

lilianweng.github.io·171w

Large Transformer Model Inference Optimization

lilianweng.github.io·174w

Some Math behind Neural Tangent Kernel

lilianweng.github.io·192w

Generalized Visual Language Models

lilianweng.github.io·204w

Learning with not Enough Data Part 3: Data Generation

lilianweng.github.io·212w

Learning with not Enough Data Part 2: Active Learning

lilianweng.github.io·220w

Learning with not Enough Data Part 1: Semi-Supervised Learning

lilianweng.github.io·231w

How to Train Really Large Models on Many GPUs?

lilianweng.github.io·241w

What Are Diffusion Models?

lilianweng.github.io·81w·Hacker News

Contrastive Representation Learning

lilianweng.github.io·258w

Reducing Toxicity in Language Models

lilianweng.github.io·268w

Controllable Neural Text Generation

lilianweng.github.io·279w

Log in to enable infinite scrolling