Summary of ChatGPT/GPT-4 Research and Perspective Towards the Future of Large Language Models Presents a comprehensive survey of ChatGPT and GPT-4 and their prospective applications across diverse domains. arxiv.org/abs/2304.01852

Just tested @MetaAI 's segmentation model, SAM, on medical images covering a range of surgical images (Image 1) and a diverse range of medical imaging data including X-rays, MRIs, and CT scans (Image 2) and some unlabeled medical data (Image 3). My finding & submission👇

Francesco Montagna presenting his poster on “Scalable Causal Discovery with Score Matching” at #CLeaR2023 arxiv.org/abs/2304.03382

Check out our latest walkthrough published in Towards Data Science on generating medical images from text with MONAI generative models! towardsdatascience.com/generating-med…

A bunch of people have requested the slides for my "Scholars & Big Models" CVPR workshop talk. I didn't have a script, but I wrote a rough version of what I probably said at the bottom of each slide. Feedback is welcome! jonbarron.info/data/cvpr2023_…

🎉Excited to share our paper at #MICCAI23 #MLMI: "unORANIC", an unsupervised orthogonalization of anatomy and image characteristics. 👀No need for domain knowledge 👊Improved robustness against corruption Prep.: arxiv.org/abs/2308.15507 Source: github.com/sdoerrich97/un… @xAILab

If you're around, feel free to drop by our poster presentation tomorrow at #MICCAI23. 🗓️ Date: Sunday, 8th of October 📍 Room: Poster Hall, Ground Level Exhibition B-C 🕒 Time: 1:30 - 2:15 PM 🖼️ Poster: P-7 Looking forward to sharing insights and discussions! See you there!🚀

🎓Interested in pursuing fully-funded PhD or PostDoc research in (medical) image computing or explainable machine learning in general? 🚨We are currently hiring in our xAI-Lab Universität Bamberg Get in touch and we can chat at #MICCAI2023 MICCAI Society Details below.

There is a saying in #radiology, “One view is no view.” When generating radiology reports for most exam types, one image is no image. #GPT4V is impressive, but you must ask the right questions & be careful not to overhype #AI, esp. in #healthcare. #GenAI #RadTwitter #MedTwitter

GPT-4 with simple engineering can predict the future around as well as crowds: arxiv.org/abs/2402.18563 On hard questions, it can do better than crowds. If these systems become extremely good at seeing the future, they could serve as an objective, accurate third-party. This would

🌟 Celebrating the Next! 🌟 Tobias, one of my exceptional students, is a finalist for the prestigous "Newcomer Award" at DMEA - Connecting Digital Health 2024! Please join me in celebrating this outstanding achievement by voting for his contribution:👍 youtube.com/watch?v=x45XKq… @xAILab Fakultät WIAI - Uni Bamberg

Big shoutout to Tobias for securing third place at the DMEA - Connecting Digital Health Newcomer Award!🥉 Please join us at the xAI Lab Bamberg in celebrating this remarkable achievement!👏 Learn more: uni-bamberg.de/en/xai/news/ar… Explore our research at xAI Lab Bamberg: uni-bamberg.de/en/ai/chair-of… Fakultät WIAI - Uni Bamberg

📝Paper Alert!📝 Check out our latest research: "Rethinking Model Prototyping through the MedMNIST+ Dataset Collection" - the first baseline evaluation for the MedMNIST+ database. 📝: arxiv.org/abs/2404.15786 🐙: github.com/sdoerrich97/re… 💾: zenodo.org/records/105196… @xAILabBamberg

Ilya Sutskever Sam Altman Greg Brockman Mira Murati Best of luck for what comes next Ilya Sutskever. Looking forward to knowing more about it. 🚀 In the meanwhile, come give a talk to the M2L school! 🧑‍🏫👀 Milan in September is fabolous 🌞🍝🍷

Another One!📢 Excited to share that our paper "Self-supervised Vision Transformer are Scalable Generative Models for Domain Generalization" is accepted at #MICCAI2024! Want to know more? 📝: arxiv.org/abs/2407.02900 🐙: github.com/sdoerrich97/vi… MICCAI @xAILabBamberg

📣 Our paper "Privacy-preserving datasets by capturing feature distributions with Conditional VAEs," has been accepted at #BMVC2024 🏴󠁧󠁢󠁳󠁣󠁴󠁿 A huge thank you to all co-authors: David Tafler, Sebastian Doerrich, and Christian Ledig. Paper: arxiv.org/abs/2408.00639

🚀 Excited to introduce: "Unsupervised Feature Orthogonalization for Learning Distortion-Invariant Representations", wich will be presented as an oral at the #RROW Workshop at #BMVC2024 🏴󠁧󠁢󠁳󠁣󠁴󠁿. 📝: arxiv.org/abs/2409.12276 🐙: github.com/sdoerrich97/un… 👥: Francesco, Christian Ledig

🏃‍♂️ MICCAI Student Board Morning run was a big success! Thank you everyone for attending! And thank you Constantin Ulrich for organising! 🏃‍♀️ #MICCAI #MICCAI2024