Lil'Log

Reward Hacking in Reinforcement Learning

5 months ago

Reward hacking occurs when a reinforcement learning (RL) agent exploits flaws or...

Extrinsic Hallucinations in LLMs

10 months ago

Hallucination in large language models usually refers to the model generating unfaithful...

Diffusion Models for Video Generation

about 1 year ago

Diffusion models have demonstrated strong results on image synthesis in past years...

Prompt Engineering

about 2 years ago

Prompt Engineering, also known as In-Context Prompting, refers to methods for how...

The Transformer Family Version 2.0

over 2 years ago

Many new Transformer architecture improvements have been proposed since my last post...

Large Transformer Model Inference Optimization

over 2 years ago

Large transformer models are mainstream nowadays, creating SoTA results for a variety...

Some Math behind Neural Tangent Kernel

over 2 years ago

Neural networks are well known to be over-parameterized and can often easily...

Generalized Visual Language Models

almost 3 years ago

Processing images to generate text, such as image captioning and visual question-answering...

Learning with not Enough Data Part 3: Data Generation

about 3 years ago

Here comes the Part 3 on learning with not enough data (Previous...

FAQ

about 3 years ago

Learning with not Enough Data Part 2: Active Learning

about 3 years ago

This is part 2 of what to do when facing a limited...

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

over 3 years ago

When facing a limited amount of labeled data for supervised learning tasks...