George Ho (@_eigenfoo) 's Twitter Profile
George Ho

@_eigenfoo

Natural language processing, Bayesian modeling, open source, crosswords, donuts and coffee. Currently ML at @flatironhealth (he/him/his)

ID: 864002389841395713

linkhttps://www.georgeho.org/ calendar_today15-05-2017 06:19:56

1,1K Tweet

1,1K Followers

715 Following

Patrick Collison (@patrickc) 's Twitter Profile Photo

Gerty and Carl Cori won the Nobel Prize together in 1947. Then 6 of their students won Nobel Prizes, all in physiology/medicine and chemistry. (Five separate prizes in total; one was shared.) amazon.com/Crucible-Scien…

George Ho (@_eigenfoo) 's Twitter Profile Photo

Today I capitulated and finally learnt how to save places on Google Maps and I think this is about to change my life Maybe my hyperfixated techie friends know a thing or two about using technology to improve lives after all

Flatiron Health (@flatironhealth) 's Twitter Profile Photo

Extracting meaningful clinical detail from EHRs for millions of patients with cancer is challenging. @FlatironHealth uses #NLP & #ML to extract key information from unstructured documents in the curation of high quality #RWD. Read more on our approach: flatiron.com/resources/appr…

Dr. Blythe Adamson (@drblytheadamson) 's Twitter Profile Photo

Flatiron Health Tweets from Zach Weinberg Big reveal of Flatiron Health #machinelearning with #language and documents in EHR. The full text explainer from our team is here: medrxiv.org/content/10.110…

<a href="/flatironhealth/">Flatiron Health</a> <a href="/zachweinberg/">Tweets from Zach Weinberg</a> Big reveal of Flatiron Health #machinelearning with #language and documents in EHR. The full text explainer from our team is here: medrxiv.org/content/10.110…
Flatiron Health (@flatironhealth) 's Twitter Profile Photo

#ML can extract clinically relevant information from EHRs at scale, but evaluating its quality has focused on single variables. This Flatiron Health study aims to evaluating ML's usefulness for research & RWE generation at scale: flatiron.com/resources/repl… Cancers MDPI

Loplop (@__loplop) 's Twitter Profile Photo

Hello, long time no #crossword! A new #cryptic is up, and I’m pretty happy with it! My favorite clue: I'm about to stuff fruit with trace of radium — it might bring death (4,6) georgeho.org/crosswords/019/

jack morris (@jxmnop) 's Twitter Profile Photo

i would retire too if i had to rewrite the entire HuggingFace Trainer to work with HuggingFace Accelerate, jesus that must have been a nightmare

Jennifer R. Weiser (@profjrweiser) 's Twitter Profile Photo

Beyond ecstatic for our Cooper Brue team from The Cooper Union for winning both best beer label and 3rd place overall in the annual beer brewing competition at AIChE. Go team and thanks Ana for helping us compete! And yes, the poster is hand drawn!

Beyond ecstatic for our Cooper Brue team from <a href="/cooperunion/">The Cooper Union</a> for winning both best beer label and 3rd place overall in the annual beer brewing competition at AIChE. Go team and thanks Ana for helping us compete! And yes, the poster is hand drawn!
George Ho (@_eigenfoo) 's Twitter Profile Photo

Hi yes hello good morning I was on a podcast, talking about crossword archivism and milk cartons You can listen to it here: podcast.data-is-plural.com/2159594/141791…

George Ho (@_eigenfoo) 's Twitter Profile Photo

I sawed my copy of the power broker in half so that it’s easier to carry around When a book’s size becomes an impediment to reading it, I feel like something’s gone seriously wrong

I sawed my copy of the power broker in half so that it’s easier to carry around

When a book’s size becomes an impediment to reading it, I feel like something’s gone seriously wrong
AK (@_akhaliq) 's Twitter Profile Photo

JPMorgan announces DocLLM A layout-aware generative language model for multimodal document understanding paper page: huggingface.co/papers/2401.00… Enterprise documents such as forms, invoices, receipts, reports, contracts, and other similar records, often carry rich semantics at the

JPMorgan announces DocLLM

A layout-aware generative language model for multimodal document understanding

paper page: huggingface.co/papers/2401.00…

Enterprise documents such as forms, invoices, receipts, reports, contracts, and other similar records, often carry rich semantics at the
Armineh Nourbakhsh (@arminehnouri) 's Twitter Profile Photo

Very excited to introduce DocLLM, a multimodal LLM developed by my colleagues J.P. Morgan. DocLLM-7B outperforms other SotA LLMs on 12/16 benchmarks within four core Document AI tasks! Incredibly proud of the team for their hard work. Check it out at arxiv.org/abs/2401.00908

Very excited to introduce DocLLM, a multimodal LLM developed by my colleagues <a href="/jpmorgan/">J.P. Morgan</a>. DocLLM-7B outperforms other SotA LLMs on 12/16 benchmarks within four core Document AI tasks!  Incredibly proud of the team for their hard work. Check it out at arxiv.org/abs/2401.00908
Pablo Montalvo (@m_olbap) 's Twitter Profile Photo

It was hard to find quality OCR data... until today! Super excited to announce the release of the 2 largest public OCR datasets ever 📜 📜 OCR is critical for document AI: here, 26M+ pages, 18b text tokens, 6TB! Thanks to UCSF Library, Industry Documents Library and PDF Association 🧶 ↓

It was hard to find quality OCR data... until today! Super excited to announce the release of the 2 largest public OCR datasets ever 📜 📜

OCR is critical for document AI: here, 26M+ pages, 18b text tokens, 6TB! Thanks to <a href="/ucsf_library/">UCSF Library</a>, <a href="/industrydocs/">Industry Documents Library</a> and  <a href="/PDFAssociation/">PDF Association</a>
🧶 ↓