LLMs mean you still need a human in the loop, but in a different part

Visually explore high-dimensional data and embeddings through interactive, smoothly-animated tours of 2D projections to build intuition for the full data manifold.

YouTube video by Open Data Science and AI Conference

The Most Satisfying Method to Explore Embeddings

This app lets you upload your vector embeddings (e.g., CSV or JSON files) and instantly creates an interactive 2‑D/3‑D plot where similar items cluster together. You can explore the layout, hover o...

Contribute to TutteInstitute/toponymy development by creating an account on GitHub.

A comprehensive look at major trends shaping the neuroscience landscape in 2025

Interactive map of 3.4 million Bluesky users, visualised by their follower pattern.

Fuzzy simplicial sets have become an object of interest in dimensionality reduction and manifold learning, most prominently through their role in UMAP. However, their definition through tools from alg...