About Cambrian

With the recent burst in ML research and LLMs, it's difficult for the general public to keep in touch with the latest developments.

For researchers, scientists, and engineers in particular, staying up-to-date with the latest ML research is a real hassle. Moreover, typical search is rarely enough.

We built Cambrian to enable a more sophisticated deep search over 240,000 machine-learning papers while continually absorbing newly released work.
Our algorithm combines classical embedding search with weights for citations and recency, awarding certain papers for impact or contribution.
We also enable rapid knowledge search through CambrianGPT, our in-house LLM for querying over individual papers.

Recent Papers ☕ ️

Get an interactive and searchable feed of today's AI research from ArXiv.

Search 🦖

Our flagship semantic search over 240,000 ML/AI papers from 2017 onwards, with CambrianGPT for custom Q&A on papers. Updates weekly.

Review 📜

Generate an automated literature review for a particular ML topic.

“I have about ~100 open tabs across 4 tab groups of papers/posts/github repos I am supposed to look at, but new & more relevant ones come out before I can do so. Just a little bit out of control.”

- Andrej Karpathy

Founded by: Siddharth Sharma, Aalok Patwa, and with engineering contributions by Mustafa Aljadery