I recently learnt about Undermind [app.undermind.ai/home/], which has revolutionized my way of literature survey in my research area. It ensures I take advantage of the most relevant research articles and gives me a chronological view of research in my field. Give it a try!👏

Update: Undermind has now expanded to include all arXiv content, so you can search across all physics, math, CS and more!

Eric Jang We built a "deep search" system to handle exactly this problem - complex tasks, where you have to dig through many papers on ArXiv. It highlights precisely relevant papers. For your search, it found ~11 papers (hope I captured what you wanted): app.undermind.ai/query_app/disp…

Undermind has just upgraded: 1) Now covers all scientific topics 2) is 10x faster than before 3) allows free unlimited usage for individuals Register and check out the new version here: undermind.ai

Finding the right papers for complex research topics can be frustrating. Undermind systematically digs through the literature to identify the precisely relevant research, as if you had sent a PhD level scientist to do hours of searching: semanticscholar.org/api-gallery/un…

I asked Undermind a really complex research question, On information related to human capital and its importance in universities, the results are very relevant, it serves as a starting point for me to understand a topic in greater depth. undermind.ai/query_app/disp…

Elicit is "working on" SPLADE! Coincidentally my last blog post was trying to understand SPLADE. Also mention of "Automated Comprehensive Search (ACS)" by Undermind something I also have blogged about. Both promising techniques (can be combined) for improving academic search

🚀 Undermind launched! Elevate your research with a radically thorough AI research assistant 🔎 "𝐴 𝑠𝑒𝑎𝑟𝑐ℎ 𝑒𝑛𝑔𝑖𝑛𝑒 𝑓𝑜𝑟 𝑐𝑜𝑚𝑝𝑙𝑒𝑥 𝑞𝑢𝑒𝑠𝑡𝑖𝑜𝑛𝑠" 💡 🌐 undermind.ai 📚 Started by two quantum physics PhDs from MIT, with decades of experience

Excited to announce that Tom and I are now in Y Combinator! See our Undermind launch below.

We're launching on Product Hunt. Support us there to help reach more researchers! producthunt.com/posts/undermin…

Check out my latest paper! We analyze the prospects of fault-tolerantly interconnecting neutral atom arrays.

Thrilled to invest in Undermind YC S24, a search engine that can handle extremely complex questions for experts like research scientists & doctors. Many YC bio-founders are paying subscribers—and investors! Backed by @Ycombinator & @Pioneer_fund. If you're a researcher

Optical cavities provide fast and non-destructive readout of individual atomic qubits; however, scaling up to many qubits remains a challenge. In a new preprint, we demonstrate site-selective cavity readout across a 10-site array using locally addressed excited-state Stark shifts

This tool is hands down the MOST powerful AI literature search engine (developed by MIT grads) It retrieved 70% of the studies I included in my systematic review (+1 new study I had missed) All by just entering my review question!

I agree. Undermind relevancy ranking is a clear step above anything I tried so far, at least for now. That's why we got subscriptions for our library. Very strong positive feedback from faculty, Research staff, phds. Not gold standard SR level (based on my test) but very good

Finding relevant papers for literature review takes a lot of time. So, MIT researchers built Undermind, an AI-powered search engine. It can generate well-researched overviews on any topic and is 10-50 times better than Google Scholar. Here's how to use it:

Here's are some of my thoughts about when to use Google Scholar vs other new "AI search tools". (1)

We used to be a society and we can be one again