AI

  • Tools for critique of art – open source

    Byscientist

    Good publication to review material: CognArtive: Large Language Models for Automating Art Analysis and Decoding Aesthetic Elements at https://arxiv.org/html/2502.04353v1 And the wonderful visualization to analyze the data over the years that was derived from WikiArt. https://cognartive.github.io Autocritic: an open-source system that uses classic art theory to evaluate images and steer generative systems. It distills historical…

  • LoRa in AI image generators

    Byscientist

    This stands for Low Rank adaptation. In AI terms, this is a small add-on to the model that makes it do specific things. It is usually used in the context of stable diffusion. A large model takes very long to train with significant resources. However, sometimes, you need specific details – for example you could…

  • Text from Image

    Byscientist

    Starting with a base image, it is possible to generate a description. An AI (Qwen-3-VL) simple description : This is a simple, hand-drawn black-and-white sketch of a person’s upper body. Here’s a breakdown of the key elements: Hair: Long, flowing hair depicted with two smooth, curved lines extending from the top of the head down…

  • |

    Engaging website

    Byscientist

    There are many ways that websites show their landing pages. Usually there are a lot of graphics. The Harvard innovation lab does it wonderfully with their landing page for one of their challenges showing particles which are responsive to mouse movement. Very dynamic and very intriguing! https://innovationlabs.harvard.edu/presidents-innovation-challenge/finalists The developer’s console tells you a bit about…

  • Sparql tool – connect LLM to knowledge graphs

    Byscientist

    Talk to knowledge graph – sparql-tool Use LLM.: Hallucinations (sometimes good for creativity), Outdated knowledge, no access to your data ( trained on public knowledge). Solutions: Fine tuning – retrain the model on domain data RAG – Search: look things up in real time. Claude code looks at searched doc. Vector embeddings: semantic similarity search…

  • Language of Graphics

    Byscientist

    Key IDEA: Chart types are great shortcuts but graphics are really sophisticated visual structures GoFish language for python using the Gestalt grouping principle. It can make graphics or chart that can display the messages that are intentional. .mark() – what shape to draw at each postion and what channels to encode part to whole relationships…

  • DeepSpot

    Byscientist

    Kalin Klonchev – the winner of a competition for AI based data analysis from Broad in 2024 had also created a tool called DeepSpot. Worth looking at for spot analysis of H&E sections by converting a full H&E slide pictures to “spots” which are analyzed. Some good links: DeepSpot paper: https://www.medrxiv.org/content/10.1101/2025.02.09.25321567v1 DeepSpot GitHub repository: https://github.com/ratschlab/DeepSpot…