🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Very interesting. ⁦AMIA⁩ cnbc.com/2024/10/29/ora…

Biologists, stop putting UMAP plots in your papers! UMAP is a powerful tool for exploratory data analysis, but without a clear understanding of how it works, it can easily lead to confusion and misinterpretation. Link to Simply Statistics blogpost below.

MICHAEL JORDAN - FAILURE (1997) "I've missed more than 9000 shots in my career. I've lost almost 300 games. 26 times, I've been trusted to take the game winning-shot & missed. I've failed over & over & over again in my life. And that is why I succeed."

This UMAP plot was generated from data simulated without inherent clusters, meaning the observed clusters are artifacts. It highlights how default Seurat clustering and UMAP settings can sometimes produce misleading patterns in data visualization.

$600 vendor-locked at-home arrhythmia detection or $75 hackable ECG system with off-the-shelf parts and open source software? introducing lattice 1. adic and I have started vessel inc. to make health monitoring and exploration more accessible. (not a medical device) 🧵

We reproduced DeepSeek R1-Zero in the CountDown game, and it just works Through RL, the 3B base LM develops self-verification and search abilities all on its own You can experience the Ahah moment yourself for < $30 Code: github.com/Jiayi-Pan/Tiny… Here's what we learned 🧵

Tip-of-the-day: quickly estimate the RAM for a N-billion parameter LLM. A good formula to know especially if you run LLMs locally.

🚨New in JAMA Internal Medicine with A Jay Holmgren Nate Apathy Julia Adler-Milstein David Bates Christine Sinsky We show that pt messages remained elevated even after the COVID pandemic, while calls peaked then dropped. Suggests that messages are net new work esp for PCPs jamanetwork.com/journals/jamai…

Announcing Minions: a method that pairs small language models on a laptop (ollama) with frontier models in the cloud—preserving 98% of the accuracy for <18% of the cost! Led by Avanika Narayan, Sabri Eyuboglu @ ICML 2025, and Dan Biderman (hazyresearch), with Together AI's Avner May. 🧵

This paper has been in the making for so long that eight children across the co-author group were born between the time we started and now! But it is finally out, and you can check it at arxiv.org/pdf/2503.13323

Stanford Medicine is orchestrating multiple agents to connect medical data, clinical trials, and more - all with the goal of delivering more effective cancer care. Incredible to see in action.

Catching up on editing chores today and one particular paper caught my attention. Nicely executed experiment in an interesting area. All 3 reporters recommended rejection because both key results are insignificant. If you know my views, insignificance does not move me

Our interpretability team recently released research that traced the thoughts of a large language model. Now we’re open-sourcing the method. Researchers can generate “attribution graphs” like those in our study, and explore them interactively.

same data

🥼 As an MD, I always believe evaluation is the cornerstone of medical AI. That's why we built PubMedQA in 2019. 🤗 Today I am very excited to share my first blog on OpenAI's HealthBench and beyond. 🔗 Please check it out: qiaojin.notion.site/eval

Launchpad's Starter Kit includes AI use cases that automate routine tasks and reduce the workloads of doctors, nurses, care teams, and administrative staff. 75% of the Epic community already has them in use. A few highlights: • Patient Summaries: Epic helps clinicians prep for

I think the issue is the "nudge" movement has misunderstood the point of the original "libertarian paternalism" paper and the "nudge" book. Original works argued that seemingly irrelevant factors can have an impact on behavior when *a set of conditions are met*🧵

Better to hire and fund people who are scrappy and hungry, who can build, who have high velocity, than the person with the fancy resume with the huge ego YC has *never* had success funding or hiring the latter "Hire for slope, not y-intercept." —Paul Buchheit

#Dataset from the Duke Radiology lung cancer screening program doi.org/10.1148/ryai.2… Duke University School of Medicine #cancer #CT #ML

Introducing FlexOlmo, a new paradigm for language model training that enables the co-development of AI through data collaboration. 🧵