Andrew Beam(@AndrewLBeam) 's Twitter Profileg
Andrew Beam

@AndrewLBeam

Machine Learning for Medicine. Assistant Prof: @Harvard | Founding Editor @NEJM_AI, Co-host AI Grand Rounds 🎙️, Co-founder @generate_biomed

ID:1244087220

linkhttp://www.beamlab.org calendar_today05-03-2013 16:21:33

5,9K Tweets

9,2K Followers

1,3K Following

Atul Butte(@atulbutte) 's Twitter Profile Photo

You were incredible in the lab, Dvir Aran, and your career is blossoming! And for the other NEJM AI podcast listeners, here’s the sign you got me, with the quote I learned from Isaac Kohane!

You were incredible in the lab, @dvir_a, and your career is blossoming! And for the other @NEJM_AI podcast listeners, here’s the sign you got me, with the quote I learned from @zakkohane!
account_circle
Andrew Beam(@AndrewLBeam) 's Twitter Profile Photo

This was such a fun conversation with a titan of biomedical informatics and healthcare data science, Atul Butte!

His creativity and energy are infectious, so skip the afternoon espresso and listen to this episode instead!

account_circle
Arjun (Raj) Manrai(@arjunmanrai) 's Twitter Profile Photo

Our conversation with the extraordinary Atul Butte
is out now on NEJM AI Grand Rounds! Atul shares his career journey, some of his secrets in giving legendary talks, and his mission to use massive data to improve health.

Episode link:

ai-podcast.nejm.org/e/an-iron-fist…

account_circle
James Zou(@james_y_zou) 's Twitter Profile Photo

⚡️Excited to share our new Nature Medicine paper where we used Twitter to build a vision-language foundation for nature.com/articles/s4159…

We curated >100K public Twitter threads w/ medical images+text to create PLIP for semantic search and 0-shot pred.

All our…

⚡️Excited to share our new @NatureMedicine paper where we used Twitter to build a vision-language foundation #AI for #pathology nature.com/articles/s4159… We curated >100K public Twitter threads w/ medical images+text to create PLIP for semantic search and 0-shot pred. All our…
account_circle
Niklas Muennighoff(@Muennighoff) 's Twitter Profile Photo

How to keep scaling Large Language Models when data runs out? 🎢

We train 400 models with up to 9B params & 900B tokens to create an extension of Chinchilla scaling laws for repeated data. Results are interesting… 🧐

📜: arxiv.org/abs/2305.16264

1/7

How to keep scaling Large Language Models when data runs out? 🎢 We train 400 models with up to 9B params & 900B tokens to create an extension of Chinchilla scaling laws for repeated data. Results are interesting… 🧐 📜: arxiv.org/abs/2305.16264 1/7
account_circle
Kristyn Beam, MD, MPH(@swanbeams) 's Twitter Profile Photo

Scheduling shifts and coverage is a time-consuming and complex process. There are many constraints, both personal and professional as well as departmentally. I tried to discuss this problem with ChatGPT today to come up with a potential solution to this issue.

account_circle
Matthew McDermott(@MattBMcDermott) 's Twitter Profile Photo

I'm going on the academic job market this fall, focused on research into knowledge and structure-augmented representation learning for health and biomedical data. Please reach out if there's a possible match with your departments or with other opportunities!

account_circle
Arjun (Raj) Manrai(@arjunmanrai) 's Twitter Profile Photo

What a pleasure to chat with the inimitable Atul Butte today for NEJM AI Grand Rounds. Sneak preview below with Atul holding a quote with his attitude towards credit assignment; episode coming soon!

What a pleasure to chat with the inimitable @atulbutte today for @NEJM_AI Grand Rounds. Sneak preview below with Atul holding a quote with his attitude towards credit assignment; episode coming soon!
account_circle
Nina Singh(@nina_singh_) 's Twitter Profile Photo

Highly recommend this fascinating NEJM AI podcast episode featuring Ziad Obermeyer discussing the future of medical AI, with a focus on tackling bias in AI models, choosing meaningful problems to solve, and cultivating interdisciplinary expertise: ai-podcast.nejm.org/e/the-double-e…

account_circle
Vivek Natarajan(@vivnat) 's Twitter Profile Photo

Medicine is inherently multimodal.

Thrilled to share Med-PaLM M, the first demonstration of a generalist multimodal biomedical AI system with a stellar team Google AI Google DeepMind Google Health

Paper: arxiv.org/pdf/2307.14334…

account_circle
Isaac Kohane(@zakkohane) 's Twitter Profile Photo

Unsurprisingly insightful take by Ziad on algorithmic bias (esp. est. total cost vs preventable cost) BUT I was nerd sniped by his trajectory [history+philosophy]->management consulting->medical school. Counterexample to the narrative of soul-sucking burnout. Worth discussing.

account_circle
Michelle M. Li (李敏蕊)(@_michellemli) 's Twitter Profile Photo

I am so proud and excited to share PINNACLE with you!

If you will be at , come find me at poster B-312 (Track: MLCSB)!

Check out the paper 🗞️: biorxiv.org/content/10.110…
Explore PINNACLE demo 🤗: huggingface.co/spaces/michell…

account_circle
Karandeep Singh(@kdpsinghlab) 's Twitter Profile Photo

T-1 week until my talk on Tidier.jl (and friends) at JuliaCon 2023 2023!

Looking forward to telling the story of the package (and now org), why it exists, how it works, and our future goals.

Come join our session (or catch the recording)!

More info: tidierorg.github.io/Tidier.jl/dev/

account_circle
Emma Pierson(@2plus2make5) 's Twitter Profile Photo

New working paper quantifying arXiv publication patterns in the age of LLMs! Joint work with Raj Movva, Sidhika Balachandar, Kenny Peng, Gabriel Agostini, and Nikhil Garg.

We analyze LLM citation patterns, fastest growing topics, many other things. Some of our findings: 1/N

account_circle
Andrew Beam(@AndrewLBeam) 's Twitter Profile Photo

What does ChatGPT-3.5* know about neonatology? A new paper in JAMA Pediatrics with Kristyn Beam, MD, MPH, Bhawesh Kumar, Cindy Wang, Dara Brodksy, and Cami Martin takes a look at this question.

We asked all 900+ questions from the well known Brodsky and Martin neonatal board prep book and had…

What does ChatGPT-3.5* know about neonatology? A new paper in @JAMAPeds with @swanbeams, @bhaweshiitk, Cindy Wang, Dara Brodksy, and @crmartin90 takes a look at this question. We asked all 900+ questions from the well known Brodsky and Martin neonatal board prep book and had…
account_circle