Know a great AI tool or AI news source? Submit it to AiByts
AiByts
Sign inGet started

posts

109 stories

Stories

← Back to the latest stories

  • Adversarial Attacks on LLMs

    The use of large language models in the real world has strongly accelerated by the launch of ChatGPT. We (including my team at OpenAI, shoutout to them) have invested a lot of effort to build default safe behavior into the model during the alignment process (e.g. via RLHF).

    Lil'Log (Lilian Weng)31 min read

  • Prompt Engineering

    Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights.

    Lil'Log (Lilian Weng)20 min read

  • The Transformer Family Version 2.0

    Many new Transformer architecture improvements have been proposed since my last post on “The Transformer Family” about three years ago. Here I did a big refactoring and enrichment of that 2020 post — restructure the hierarchy of sections and improve many sections with more recent papers.

    Lil'Log (Lilian Weng)46 min read

  • Large Transformer Model Inference Optimization

    [Updated on 2023-01-24: add a small section on Distillation.] Large transformer models are mainstream nowadays, creating SoTA results for a variety of tasks. They are powerful but very expensive to train and use.

    Lil'Log (Lilian Weng)27 min read

  • Some Math behind Neural Tangent Kernel

    Neural networks are well known to be over-parameterized and can often easily fit data with near-zero training loss with decent generalization performance on test dataset.

    Lil'Log (Lilian Weng)23 min read

  • How to enhance multiple photos at once online

    Photo enhancement takes time — especially if it’s not just “for a show”, but a real deep enhancement with the help of AI technologies. We bet you have better plans than just sitting in front of the laptop and waiting while a picture is being processed to upload a new one!

    Neural Love Blog3 min read

  • Generalized Visual Language Models

    Processing images to generate text, such as image captioning and visual question-answering, has been studied for years. Traditionally such systems rely on an object detection network as a vision encoder to capture visual features and then produce text via a text decoder.

    Lil'Log (Lilian Weng)21 min read

  • How to enhance your spider online with the power of AI

    Hello, that is Denis. At neural.love we are focusing on resolving the real-life problem with the help of machine learning, and today I want to cover another essential scenario that almost any modern person asks themselves today “How do I enhance my spider???”.

    Neural Love Blog2 min read

Showing 90 of 109 stories

Load more stories
AiByts Weekly Brief

Get the top AI news and tools straight to your inbox every week.

Weekly · AI news

Join 15,000+ AI enthusiasts