Concerning results: We've evaluated Transformer-, Mamba-, and CNN-based architectures, revealing widespread validation flaws in #MedicalImageSegmentation. Many claims of superiority do not withstand strict testing. Time to push for rigor in the field :) arxiv.org/pdf/2404.09556…

Code is here: github.com/MIC-DKFZ/nnUNet Enjoy!

🚀 New Paper Alert! 🚀 "Radiomics workflow definition & challenges - German priority program 2177 consensus statement on clinically applied radiomics" 🌐Check out the paper here: insightsimaging.springeropen.com/articles/10.11… 💡Project resources: github.com/MIC-DKFZ/radio…

👏🏻 Congratulations to Adway Kanhere, Software Engineer at the Univ. of Maryland, for winning the Best Poster Award at the #CVPR2025 2024 Workshop: Data Curation and Augmentation in Medical Imaging! 🌼 🚀 Workshop: buff.ly/3Vduwbm 📖 Paper: buff.ly/4eAx7ou

🗓️ Flower Monthly is this Wednesday! 🤩 🔗 Link to join: buff.ly/432pi5K 📆 Jul 16:00 UTC 1️⃣ Dr. Siba Haidar (Siba Haidar) Associate Professor from Learning Data Robotics (LDR) at ESIEA 2️⃣ Adway Kanhere (Adway Kanhere) Software Engineer from Univ. of Maryland

I am excited to be giving a 4-hour tutorial on "Pretraining and Finetuning LLMs from the Ground Up" at the SciPyConf conference in 5 days! This tutorial is aimed at coders interested in understanding the building blocks of large language models (LLMs), how LLMs work, and how to

Project that blew my mind a bit earlier and I still think about often: A Trustworthy, Free (Libre), Linux Capable, Self-Hosting 64bit RISC-V Computer contrib.andrew.cmu.edu/~somlo/BTCP/ This is an attempt to build a *completely* open source computer system, both software AND hardware.

Introducing Meta Segment Anything Model 2 (SAM 2) — the first unified model for real-time, promptable object segmentation in images & videos. SAM 2 is available today under Apache 2.0 so that anyone can use it to build their own experiences Details ➡️ go.fb.me/p749s5

Are you writing an ICLR paper, and wondering... * What level of detail should the background have? * Why do people read related work? * How do I convey convincing results? I have some mostly satisfactory answers to these questions. youtu.be/qNlwVGxkG7Q?si…

Manim: Python library for math animations

Our first short course with Anthropic! Building Towards Computer Use with Anthropic. This teaches you to build an LLM-based agent that uses a computer interface by generating mouse clicks and keystrokes. Computer Use is an important, emerging capability for LLMs that will let

7. OpenAI launched Deep Research, a new Pro ChatGPT feature that performs in-depth web research, analyzing text, images, and PDFs to deliver detailed reports with citations in under 30 minutes.

This paper is wild - a Stanford team shows the simplest way to make an open LLM into a reasoning model. They used just 1,000 carefully curated reasoning examples & a trick where if the model tries to stop thinking, they append "Wait" to force it to continue. Near o1 at math.

President of OpenAi, Greg Brockman shares the way to create a perfect prompt:

This is interesting as a first large diffusion-based LLM. Most of the LLMs you've been seeing are ~clones as far as the core modeling approach goes. They're all trained "autoregressively", i.e. predicting tokens from left to right. Diffusion is different - it doesn't go left to

Course material for an MIT class "Introduction to Flow Matching and Diffusion Models", looks great if you want a principled and hands on understanding of diffusion models/flow matching

Introducing our first set of Llama 4 models! We’ve been hard at work doing a complete re-design of the Llama series. I’m so excited to share it with the world today and mark another major milestone for the Llama herd as we release the *first* open source models in the Llama 4