Tag
This paper develops and evaluates a six-phase workflow using generative AI to create accessible interactive visualizations for undergraduate mathematics without programming, achieving WCAG 2.2 Level AA compliance across multiple tools.
This article provides an interactive exploration of the Moon's celestial mechanics, including its orbit, phases, and gravitational effects, through simulations and explanations.
An interactive and animated tool for visualizing the architecture of any HuggingFace models, useful for developers and researchers.
An interactive web visualization that reconstructs today's countries and cities on Earth's tectonic plates across deep time and into the future using the Merdith 2021 plate model and pyGPlates.
An animated, Rollercoaster Tycoon-inspired interactive visualization explains the chip manufacturing process by following a wafer through each stage of production.
An interactive map of GPT-2's token embedding space that lets users tap any token to explore its embeddings.
WikiStar is a system that uses an LLM classifier to tag scientifically meaningful edits in Wikipedia article revision histories, enabling interactive exploration of how scientific knowledge evolves over time. The system includes a benchmark dataset and was validated through a user study with domain experts.
Points out that current AI code understanding tools like Codex/Cursor can only provide static text or Mermaid diagrams, while modus can generate interactive diagrams and sandbox HTML in conversation, allowing users to intuitively understand code architecture through dragging and clicking, demonstrated with the Codex CLI source code as an example.
An interactive article explaining the intricate mechanics of a mechanical watch movement, from the mainspring to the timekeeping system.
TraceScope provides an interactive web-based tool for exploring semantic flows of recent AI papers from arXiv, with an open-source library available on GitHub.
This interactive tool visualizes the mathematical underpinnings of transformer models through dataflow graphs, covering architectures from GPT-2 to Qwen 3.6 and various attention mechanisms.
Transformer Explainer is an interactive visualization tool that allows non-experts to understand the inner workings of the GPT-2 model through real-time experimentation and visualization in a web browser.