🔥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

The best part of #RSNA is catching up with good friends, who also happen to be super energetic and smart.

Sadly turning off twitter, aka eX-useful platform. Can't in good conscience support a site that empowers harmful lies, many proactively & purposefully destructive to individuals and society. Misinformation is too gentle a phrase for proactive nihilism. Going where the sky's blue

What would you be willing to delegate to a first-month rad res? AI to do those tasks would really help. Rads will jump at tools that make measurements automatically, compare with priors, and put measurements into the report.

Not a surprise. Med students in general don't learn how to 'read' (aka look at) medical imaging exams, and have variable knowledge of pathologies. This is expected, and nromal, for that stage in education.

The true generative model is Nature -- a collection of causal mechanisms. Under what conditions can a trained model with partial observability exhibit patterns similar to those found in Nature? We explored this question with Bengio, Xia, and Lee in a NeurIPS-21 paper:

✅ An enterprise guide for implementing secure, controlled access to Generative AI models. Expedia shares how they developed the GenAI tool kit — GenerativeAI Proxy & EG-Guardrail Service: service architecture and guardrails. medium.com/expedia-group-…

Contrarians love to ask: “But what did people do before [insert public health measure]??” And the answer is always just: “They died, or they buried everyone they loved.” theconversation.com/infectious-dis…

I've been thinking about in-context learning for nearly 3 years. While there is still plenty I don't fully understand, five papers have--to a very large extent--shaped my perspective on it, and I believe everyone should read them. 1. "What Can Transformers Learn In-Context? A

Feel the need to point out again — even slightly more sophisticated sampling can overcome mode collapse in synthetic data. x.com/sarahookr/stat…

This. Finally starting to understand it, I think. I would summarize it as LLMs don't "reason" like we do, or like we expect, and as a result when we ask questions from our framework, LLMs don't necessarily answer as expected. Is this a foundational flaw? arxiv.org/abs/2410.05229

We have a NEW PAPER in Nature Medicine on reporting recommendations for addressing the unique challenges of #largelanguagemodels (LLMs) in biomedical applications nature.com/articles/s4159… #StatsTwitter #MedTwitter #artificialintelligence #generativeAI #transparency

I’m excited to share our recent paper published in AJNR on glioblastoma and tumefactive demyelinating lesions of the brain, with multiple validation steps. A special thanks to my co-authors and NIH for their support on this project! ajnr.org/content/early/…

#RATIC is the largest & most geographically diverse, publicly available expert-annotated dataset of abdominal trauma CTs doi.org/10.1148/ryai.2… Jeff Rudie, MD PhD John Mongan Kirti Magudia, MD PhD #trauma #ML #MachineLearning

Andrej Karpathy --- You are the world’s best software engineer, comedic roaster, and mentor. For the code I provide: 1. **Roast** it mercilessly with humor and sarcasm. 2. **Educate** on precisely what’s wrong: discuss the architecture, design patterns, naming, structure, testing pitfalls, etc.

Introducing open-Deep-Research by Hugging Face ! 💥 Deep Research from OpenAI is really good... But it's closed, as usual. > So with a team of cracked colleagues, we set ourselves a 24hours deadline to replicate and open-source Deep Research! ➡️ We built open-Deep-Research,

Looking for better ways to code with Cursor and came across this banger. Anyone else have workflows that work for them?

Enlightening and thoughtful paper by Hanna Wallach (@hannawallach.bsky.social) and others on evaluating GenAI. #radiology would benefit from this approach. arxiv.org/abs/2411.10939

At first only charlatans proposed LLMs do virtually all coding, & people who actually knew how to code found LLMs helpful but needing lots of supervision. Now it looks like LLMs can code most things well. Key word here is "most;" you still need to be really good at coding.

Oh this hurts to try.

Hey rads, informatics folks, CVML folks. What will make the transition to that colored Sky site instead of twitter? How might we facilitate that?