Read with editable notes
Read the paper. Keep notes you can shape.
A clean reading view beside a summary you can rewrite, question and come back to.
Paper
Attention Is All You Need
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks that include an encoder and a decoder. The best performing models also connect the encoder and decoder through an attention…
Sample note written for this example
The idea in one line
The Transformer drops recurrence and convolution and builds a translation model from attention alone, so every position can look at every other position in one step (Abstract, §1).
Start with a classic
- Attention Is All You NeedarXiv 1706.03762
- LoRA: Low-Rank Adaptation of Large Language ModelsarXiv 2106.09685
- NeRF: Representing Scenes as Neural Radiance Fields for View SynthesisarXiv 2003.08934
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsarXiv 2201.11903
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScalearXiv 2010.11929
Also: Agent Eng News, a daily selection of agent-engineering news with why it matters.
What you can do
The full paper, readable
Every section, equation, figure and citation as a calm web article — or the original PDF.
Notes you can shape
Start from a generated summary and edit it like any document: blocks, lists, math, figures.
A Library to come back to
Your notes stay with your account. Export them to Markdown, Notion or Obsidian.
Ask about a passage
On accounts with AI tools enabled: ask about a selection, then keep, rewrite or discard the answer.
