Earlier this year, we released the BIOMEDICA dataset, featuring 24 million unique image caption pairs and 30 million image references derived from open-source biomedical literature. It's been great to see the community engaging with it—we're currently seeing around 6K downloads

Excited to see SmolVLM powering BMC-SmolVLM in the latest BIOMEDICA update! At just 2.2B params, it matches 7-13B biomedical VLMs. Check out the full release: Hugging Face #smolvlm

🤗The SmolVLM report is out, with all the experiments, findings, and insights that led to high performance at tiny sizes🤏. 📱These models can run on most mobile/edge devices. 📖Give it a look!

Three papers being presented by my amazing collaborators at #ICLR2025! 🌟 (sadly I can't make it) 1. Mechanistic Interpretability Meets Vision Language Models: Insights and Limitations 🔍 A deep dive into mechanistic interpretation techniques for VLMs & future

I'm at #ICLR2025 presenting "Video Action Differencing". Keen to chat with anyone interested in MLLMs - both for general data & for scientific reasoning

My lab is starting at UW-Madison! This is a unique opportunity to contribute to impactful computational neuropathology research in a collaborative environment. Join the Nirschl Lab and help drive discoveries that improve our understanding of neurodegenerative disorders!🧠

I'm at CVPR! Come see me at one of my posters, or reach out for a chit chat. MicroVQA: reasoning llm benchmark in biology Sat 5-7pm, hall D, poster #357 jmhb0.github.io/microvqa/ BIOMEDICA: a massive vision-language dataset Sat 5-7pm, hall D, poster #374 minwoosun.github.io/biomedica-webs…

Get around our very cool #ICML paper that predicts how biological cells respond to drug treatments or gene knockdowns. It was led by the legendary Yuhui Zhang and @hhhhh2033528, and I was happy to contribute a tiny bit :)

I've been working with the Reflection AI team on Asimov, our best-in-class code research agent. I am super excited for you all to try it. Let me know here if you want to try it and I can move you off the waitlist. :)

“Make it red.” “No! More red!” “Ughh… slightly less red.” “Perfect!” ♥️ 🎚️Kontinuous Kontext adds slider-based control over edit strength to instruction-based image editing, enabling smooth, continuous transformations!

Thinking about using small multimodal models? Want a clearer understanding of what breaks when downscaling model size, and why? ✨Introducing our new work on Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models 🧵👇