Yannick Zoetgnande
yannickzoet.bsky.social
Yannick Zoetgnande
@yannickzoet.bsky.social
Reposted by Yannick Zoetgnande
Happy New Year! To kick off the year, I've finally been able to format and upload the draft of my AI Research Highlights of 2024 article.
It covers a variety of topics, from mixture-of-experts models to new LLM scaling laws for precision:
Noteworthy AI Research Papers of 2024 (Part One)
Six influential AI papers from January to June
magazine.sebastianraschka.com
January 1, 2025 at 2:12 PM
Reposted by Yannick Zoetgnande
Coucou, il y a du monde ici?
Je crois que je vais être de plus en plus actif sur cette appli où le ciel est bleu. On va parler astronomie, sciences et apprendre en s'émerveillant!

N'hésitez pas à partager pour recréer une belle communauté ici!!
November 17, 2024 at 8:54 AM
Reposted by Yannick Zoetgnande
Medically adapted foundation models (think Med-*) turn out to be more hot air than hot stuff. Correcting for fatal flaws in evaluation, the current crop are no better on balance than generic foundation models, even on the very tasks for which benefits are claimed.
arxiv.org/abs/2411.04118
Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?
Several recent works seek to develop foundation models specifically for medical applications, adapting general-purpose large language models (LLMs) and vision-language models (VLMs) via continued pret...
arxiv.org
November 26, 2024 at 6:12 PM
Reposted by Yannick Zoetgnande
get it while it’s hot #ai

go.bsky.app/Pxcnfu6
November 18, 2024 at 1:36 PM