Why do I have to pretend that I'm going to print something in order to save it as a PDF. Why do I have to engage in a little ruse.

We are excited to release the weights of @msftresearch.bsky.social's COLIPRI, our 3D vision–language encoder for chest CT scans, on @hf.co 🤗 Model: aka.ms/colipri Demo: aka.ms/colipri-demo Paper: aka.ms/colipri-paper Why does COLIPRI matter? 🧵0/12 👇

Grading and googling hallucinated citations, as one does nowadays, and now that LLMs have been around for a while, I've discovered new horrors: hallucinated journals are now appearing in Google Scholar with dozens of citations bc so many people are citing these fake things

This article frames the problem as [AI?] slop. Which is a problem, but not the main one here. This is an issue with authorship norms and practices. A single individual putting their name on hundreds of (workshop) papers they admitted they had little part in.

Excited to speak shortly at the Medical Imaging at @euripsconf.bsky.social workshop in Copenhagen, where I'll share some insights from our @msftresearch.bsky.social team's journey "From medical image interpretation to scientific discovery" over the past couple of years.

SpaceX is ready for its next Transporter mission! With 140 satellites onboard, this is the largest Transporter mission since Transporter-1 in 2021, which carried 143 satellites. Here's my identification attempt. Launch is scheduled for NET 18:19 UTC.

TLDR; The PSF has made the decision to put our community and our shared diversity, equity, and inclusion values ahead of seeking $1.5M in new revenue. Please read and share. pyfound.blogspot.com/2025/10/NSF-... 🧵

🩻Excited to share our latest preprint: “Data Scaling Laws for Radiology Foundation Models” Foundation vision encoders like CLIP and DINOv2 have transformed general computer vision, but what happens when we scale them for medical imaging? 📄 Read the full preprint here: arxiv.org/abs/2509.12818

Recognition is no doubt significant but it will be a hollow gesture if the UK does not also seek to end Israel's genocide, illegal occupation, and system of apartheid against the Palestinian people. 🧵1/3

Yeah man we should really fight back by staying on X

Having some fun with DINOv3 and PCA! Although I'm not happy my nose has such a low foreground probability :D

Email addresses are very simple, and you will score highly in this quiz. e-mail.wtf

Introducing DINOv3 🦕🦕🦕 A SotA-enabling vision foundation model, trained with pure self-supervised learning (SSL) at scale. High quality dense features, combining unprecedented semantic and geometric scene understanding. Three reasons why this matters👇

We’re not sure who needs to hear this, but ‘blueberry’ has two b’s.

Boiling here at home in Cyprus but I put the finishing touches a couple of days ago on this preprint: What Does 'Human-Centred AI' Mean? doi.org/10.48550/arX... Wherein I analyse HCAI & demonstrate through 3 triplets my new tripartite definition of AI (Table 1) that properly centres the human. 1/n

Scientists overwhelmingly recognize the value of sharing null results, but rarely publish them in the research literature go.nature.com/450KElr

i love it when people make PRs really easy to review ❤️ feels really bad when there's a PR that's been open for a while, but i know i can't easily do a good job of reviewing it, so it's constantly "later"

New 2 year position as an Imaging Data Infrastructure Specialist Located a the Hunter Medical Research Institute (HMRI) & the University of Newcastle (UoN), in partnership with the National Imaging Facility (NIF), Apply here: www.seek.com.au/job/85537666

A #computervision researcher at #ICML2025

New work from my team! arxiv.org/abs/2507.12950 Intersecting mechanistic interpretability and health AI 😎 We trained and interpreted sparse autoencoders on MAIRA-2, our radiology MLLM. We found a range of human-interpretable radiology reporting concepts, but also many uninterpretable SAE features.

Just published in JOSS: 'Lighter: Configuration-Driven Deep Learning' https://doi.org/10.21105/joss.08101

The world’s first multimodal, bilingual radiology dataset could reshape the way radiologists and AI systems make sense of X-rays. PadChest-GR, developed by the University of Alicante with Microsoft Research, has the potential to advance research across the field for years to come. msft.it/6013SLDYZ

📣 Our new PadChest-GR benchmark in collaboration with @ua.es and MedBravo is published in @ai.nejm.org: ai.nejm.org/doi/full/10....! 📰 Also check out our blog post for why we're so excited about it: www.microsoft.com/en-us/resear... 💾 The dataset can be downloaded here: bimcv.cipf.es/bimcv-projec...

A novel dataset designed to train and evaluate grounded report generation models from chest x-ray images includes comprehensive sentence-level bounding-box annotations for all clinically relevant findings in each image. Learn more: nejm.ai/44rk1a1 @dccastr0.bsky.social #AI #MedSky #MLSky

codingAssistantsAreJustCasinosForProgrammers

Congratulations/enhorabuena to @dccastr0.bsky.social and the rest of the team 👏 One important step towards usability of AI in real-world radiology applications.

Demystifying conda packages!

A new use of the asterisk in the paper author list for credit assignment

I asked "on the other platform" what were the most important improvements to the original 2017 transformer. That was quite popular and here is a synthesis of the responses:

Some of the anti-AI stuff feels a bit like when people would say "don't use Wikipedia as a source." It's just like anything else, a piece of information that you weigh against multiple sources and your own understanding of its likely failure modes

One weird trick for better diffusion models: concatenate some DINOv2 features to your latent channels! Combining latents with PCA components extracted from DINOv2 features yields faster training and better samples. Also enables a new guidance strategy. Simple and effective!

Al papa lo que es del papa.

I wrote this to help my team build an Operational Excellence mindset. I actually shared it internally with the whole company. Sharing it here in case it's useful to someone: docs.google.com/document/d/1...

Gemini 2.5 Pro and Flash now have the ability to return image segmentation masks on command, as base64 encoded PNGs embedded in JSON strings I vibe coded an interactive tool for exploring this new capability - it costs a fraction of a cent per image simonwillison.net/2025/Apr/18/...

A while back, I worked on some tooling to export all Spain's National Institute of Statistics datasets to Parquet and published them to @hf.co. davidgasquez.com/exporting-in... I'm now looking for ways to run this weekly, ideally, on free infrastructure. Ideas?

🔗 Websites vanish. Links break. But knowledge can live on with your help. Use the Wayback Machine’s Save Page Now tool to archive webpages that are important to you. 🕰️ 💾 📌 Try it now: web.archive.org/save

Inspired by itry, I’ve written jtry. It creates a temporary folder with a virtual environment managed by uv containing the passed packages and an empty Jupyter notebook, then opens the notebook in VS Code. Try e.g. curl raw.githubusercontent.com/fepegar/jtry... | bash -s -- transformers pydantic

Quick TIL: if you have uv installed and you want to try out ANY Python package in an ipython REPL, you can do so just by running uvx --with llm --with sqlite-utils ipython Pass as many --with package options as you like I wrapped it in a shell script, "itry llm" til.simonwillison.net/python/itry

These are the countries that have already banned hitting children. We're supporting a push from @jessasatomp.bsky.social to add England to this list.

CERN will provide financial incentives to encourage practices such as data sharing and transparent peer review https://go.nature.com/4geENfM

Para que quede claro.

Pues para no ser un pato, lo parece

debugging github actions

Great read. “Once there is a concrete path to revenue […], it becomes increasingly more difficult for researchers to continue to ask for full research freedom. Many will be asked to directly contribute to products […], and only a few will be allowed continued freedom in research.”

I gave most of the frontier models this prompt: "create something I can paste into p5js that will startle me with its cleverness in creating something that invokes the control panel of a starship in the distant future" Here is what they did (I didn't include Gemini 1.5, it kept making errors)

31% of US adults use generative AI for healthcare 🤯But most AI systems answer questions assertively—even when they don’t have the necessary context. Introducing #MediQ a framework that enables LLMs to recognize uncertainty🤔and ask the right questions❓when info is missing: 🧵

Lidong Zhou giving lessons on scaling from the systems community #NeurIPS2024