Product

Highlight and annotate any web page

Select text on any page, add a note and tags, and it is saved with its source. Save the page to your Library and it becomes a citable, verifiable source. Follow the journals of your field in the same place.

Free plan · No credit card · Chrome and Firefox

arxiv.org/abs/1706.03762
arXiv:1706.03762 · cs.CL

Attention Is All You Need

Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin · 2017

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 mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train.

Web highlighter

Highlights that keep their source

The extension works on the live page in Chrome and Firefox. Every highlight carries a required comment, tags, a colour and a visibility: private, public or shared with a space. Reopen the page and the highlights are back in place.

arxiv.org/abs/1706.03762
arXiv:1706.03762 · cs.CL

Attention Is All You Need

Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin · 2017

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 mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train.

app.viteresearch.com/library/sources
Attention Is All You Need
arxiv.org · Vaswani et al. · 2017 · saved 4 Sept 2026
Verified · snapshot v2monthly checks3 quotes
SHA-2569f2c…e41aDOI10.48550/arXiv.1706.03762CiteAPA 7 · MLA 9 · Chicago · BibTeX
Vaswani, A., Shazeer, N., Parmar, N., … (2017). Attention is all you need.arXiv. https://arxiv.org/abs/1706.03762 · Archived at Vite Research, 2026-09-04 (snapshot v2)
Copy APA
Change historyNo change since the first snapshot · next check 4 Oct 2026
unchanged
Library and citations

Sourced by default, cited in one click

Save a page from the extension, paste a link, or import BibTeX, RIS, CSV or bookmarks. Each source keeps a snapshot with a SHA-256 hash, its metadata and your quotes, can be monitored for changes, and is cited in APA 7, MLA 9 or Chicago.

Collections

A home for every source

Group highlights, web pages, documents and images into collections by project, topic or thesis. Three collections on the free plan, unlimited on Pro; a space has its own collections tab.

app.viteresearch.com/develop/collections
Collections
3 collections · annotations, web pages, documents, images
Transformer architectures14 highlights · 6 web pages · 2 documents
open
Sleep and memory9 highlights · 3 web pages
open
Policy sources · shared with Climate risk review21 items · space
space
app.viteresearch.com/develop/notes

2.1 Attention mechanisms

The field turned on one architecture; [[Transformer]] links the definition note.

"We propose a new simple network architecture, the Transformer…" · highlight · arxiv.org/abs/1706.03762

Complexity per layer: $O(n^2 \cdot d)$ for self-attention.

graph LR; A[Encoder] --> B[Decoder]

- [ ] Compare with recurrent baselines
- [x] Add the citation (APA 7)

Research notes

An editor built for thinking

Write in a clean editor with headings, lists, task lists, blockquotes, code blocks, images, math with KaTeX and Mermaid diagrams. Embed your saved highlights and articles, link notes with wiki-links, and export Markdown.

Source feeds

Never miss what is worth reading

Add any RSS or Atom feed, or pick one from the catalogue, and read new articles in one stream. From an article: highlight it, save it to a project or a space, bookmark it, mark it read. Feeds are free and unlimited.

app.viteresearch.com/discover/stream
Stream · Today
3 feeds · 12 new articles
Nature Neuroscience · latest articlesNew issue · 4 articles · 2 h ago
annotate
arXiv q-bio.NC · Neurons and Cognition6 new preprints · today
save to project
PubMed · "sleep AND memory consolidation"2 new results · bookmarked 1
bookmark
Environmental Policy and GovernanceTable of contents · 1 d ago
read
app.viteresearch.com/share/spaces
Climate risk review · space
owner, 1 admin, 2 members
Mara · 10:12Shared the IPCC synthesis highlight to the space: it is the number for the summary.
You · 10:14Saved it to the Library with monitoring on; citation is in the collection.
Jon · 10:20Added two feed articles from Nature Climate Change to the shared list.
Collaborative spaces

Build a shared brain with your team

A space is a group with owner, admin and member roles. Share highlights, feed articles, collections and sources into it and talk it through in real-time chat. Spaces are part of the Pro plan.

And more

The details that make it fast

Sync between app and extension

Sign in once; the extension picks up your session. Capture in the browser, write in the app.

Search

Search highlights by tag from the header, and your Library in full text, including the archived page text.

Tags and labels

Flexible tags across highlights, quick captures and sources.

Private by default

Highlights are private unless you make them public or share them to a space. All traffic to our servers uses HTTPS.

Export anytime

Markdown from notes; BibTeX, CSV and JSON from the Library; evidence packs on Pro.

Public source links

Share a preserved source as a public page with its citation; revoke it any time.