🔥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

ControlNet is a structure to control diffusion models by adding extra conditions proposed by style2paints. Thanks to Mark Graham and Virginia Fernández, now we have a tutorial on controlnets to generate brain images. Check it out on MONAI Generative Models! tinyurl.com/mukfhmy7

📢We have an opening for a #DataScience technician in #MachineLearning based #disease and #treatment response #prediction. 🌍Apply by September 21 to join our #international and #interdisciplinary team! #aijobs #JobOffer 👇 euraxess.ec.europa.eu/jobs/108664

📢 PhD/PostDoc Opportunity Fully-funded (healthcare, pension, >50T€ pa) position in my group Universität Bamberg Opportunity for impactful ML/CV research and to publish & attend prestigious conferences (e.g., CVPR/ICCV/MICCAI). Topic flexible. Details below. Please share/RT🙏

Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models paper page: huggingface.co/papers/2311.12… present a method to create interpretable concept sliders that enable precise control over attributes in image generations from diffusion models. Our approach identifies a

This time last year, we published a #review on #medical image #generation. After receiving feedback, we included #SynTRUST - a meta-analysis framework to systematically analyse #reproducibility & #generalizability of image synthesis studies. More here: sciencedirect.com/science/articl…

LooseControl was just released and it's so good! 🔥 It enables depth-map conditioned image generation, but unlike ControlNet, the 3D boxes enable less strict control with simple bounding boxes. And look at how stable it is across frames! More examples (with code) below ⬇️⬇️

If you’re interested in equitable and trustworthy AI, I recommend this article on skin tone fairness in dermatological AI! linkedin.com/pulse/does-you… You can also find the full paper here: link.springer.com/chapter/10.100… And the published code: github.com/tkalbl/Revisit…

💡Bias in computer-aided detection systems for #breastcancer is increasing risk of late cancer detection in high-density breasts. 📚Read this paper to see how we aim to improve the mass detection performance in high-density breasts: frontiersin.org/journals/oncol… #worldcancerday

Excited to share that #FreeU is accepted to #CVPR2025 #CVPR2024 . FreeU has been integrated into Hugging Face diffusers🚀 FreeU+SDXL Gradio demo: huggingface.co/spaces/Chenyan… -Code: github.com/ChenyangSi/Fre… Great team effort w/ Ziqi Huang Yuming Jiang Ziwei Liu

🎉 medigan, by Richard Osuala, is an open-source🐍library. 🔎Easily search and find generative models 🎁Reuse existing models instead of training your own ⬆️Share your own model to boost visibility and impact. 🖥️github.com/RichardObi/med… 📄shorturl.at/deIUW #MachineLearning

📢 Job opportunities at Artificial Intelligence in Medicine Lab * BCN-AIM! A research technician/data scientist and a postdoc position in Barcelona. euraxess.ec.europa.eu/jobs/205184 euraxess.ec.europa.eu/jobs/205202

Dr Maciej Bobowicz of Gdański Uniwersytet Medyczny (GUMed) shared with us the goals of the #EuCanImage project! Check out the video: youtube.com/watch?v=-Ff50n…

Ready to join the city of European legends? ⚽🤖 Our #Cardiology team is looking for an enthusiastic Postdoc to join our international team in stunning Barcelona! 🌍✨Sounds interesting, apply here by 1 August: seu.ub.edu/ofertaPublicaC… #PostdocOpportunity #ResearchJobs

Exciting times for our oncology team, presenting our latest research at the ACMCV 2024 on Sept 17. 📖Read the🧵for paper details! #AIResearch #MedicalImaging #Radiomics #CancerResearch #Oncology

All of my group will be presenting: Main conference: @spieker_vj (oral), Cosmin Bercea, Hannah Eichhorn, Valentin Koch , Maxime di Folco, Stefan Fischer, Anna Reithmair Richard Osuala Richard Osuala - with Karim Lekadir! Marta Hasny (oral) on her MSc with Reza Nezafat

🎉 Our PhD student Richard Osuala presents at #MICCAI2024! His paper on multi-conditional latent diffusion models could revolutionise DCE-MRI without the need for contrast agents. Catch his poster today! Full paper: link.springer.com/chapter/10.100… 💡🧠 #AIinHealthcare #MedicalImaging

Our latest work improves chest x-ray report generation with LLM alignment tools! We build a scalable preference fine-tuning pipeline to improve automated metrics + expert rad. win rates—all WITHOUT any radiologist feedback. Preference alignment w/o needing human preference. 1/3

Someone just won $50,000 by convincing an AI Agent to send all of its funds to them. At 9:00 PM on November 22nd, an AI agent (Freysa) was released with one objective... DO NOT transfer money. Under no circumstance should you approve the transfer of money. The catch...?

The (true) story of development and inspiration behind the "attention" operator, the one in "Attention is All you Need" that introduced the Transformer. From personal email correspondence with the author 🇺🇦 Dzmitry Bahdanau @ NeurIPS ~2 years ago, published here and now (with permission) following

FID has many limitations for medical images (e.g., downstream task misalignment). Introducing the Fréchet Radiomic Distance (FRD): a metric designed from the ground up for better characterizing medical images, led by me and Richard Osuala! Code/paper: github.com/RichardObi/frd…