For papers, textbooks and lecture notes
Highlight anything you read. Watch it explained.
Select a line in any PDF and xplain talks you through it while it draws, like a teacher at a board. Stop it with a question whenever you like.
Put xplain.to/ in front of any arXiv or PDF link. Or open a file from your computer. No account needed.
We call our particular attention “Scaled Dot-Product Attention”. The input consists of queries and keys of dimension dk, and values of dimension dv.
Three steps, and the hard paragraph makes sense.
- 01
Select what confuses you
Highlight a sentence, or draw a box around a figure, a table or an equation. PDFs, slides and photos of a page all work.
- 02
Listen and watch
xplain explains it out loud while it draws on a board. Each drawing appears on the word that names it, like a teacher at a whiteboard.
- 03
Interrupt any time
Ask by typing or just by speaking. Click anything on the board and ask why it is there. It answers, then picks up where it stopped.
A chatbot gives you a wall of text. xplain gives you the board.
Same question: “what does the derivative at a point mean?”
The derivative f′(a) is defined as the limit of the difference quotient (f(a+h) − f(a))/h as h approaches 0. Geometrically, the difference quotient is the slope of the secant line through (a, f(a)) and (a+h, f(a+h)). As h shrinks, the secant line rotates toward the tangent line, and its slope converges to f′(a), which is the instantaneous rate of change of f at a. For example, if f(x) = x², then (f(a+h) − f(a))/h = 2a + h, which tends to 2a…
“Watch the dashed line. As the second point slides toward a, it turns into the yellow tangent. Its slope is the derivative.”
Try it on a famous paper
Each one opens in the reader. Select any sentence and press Explain.
- Attention Is All You NeedarXiv, 2017xplain.to/arxiv.org/abs/1706.03762
- Deep Residual Learning for Image RecognitionarXiv, 2015xplain.to/arxiv.org/abs/1512.03385
- Denoising Diffusion Probabilistic ModelsarXiv, 2020xplain.to/arxiv.org/abs/2006.11239
- Adam: A Method for Stochastic OptimizationarXiv, 2014xplain.to/arxiv.org/abs/1412.6980
Export the lesson
Download any explanation as a narrated MP4 to rewatch or share with a class.
In your language
The paper can be in English and the explanation in yours.
Any subject
Calculus, transformers, biochemistry, physics. If it is on the page, it can be drawn.