In a world of Donald Trumps, be a Bishop Mariann Edgar Budde.

We explain 🥥COCONUT (Chain of Continuous Thought), a new paper using vectors for CoT instead of words. We break down: - Why CoT with words might not be optimal. - How to implement vectors for CoT instead words and make CoT faster. - What this means for interpretability.

🎙️ Yesterday, I gave a keynote on large language models outfitted with visual understanding, and the faithfulness of their chain-of-thought reasoning at the National Conference on Governing the Digital Society and Human-Centered AI. 📍 Hosted at the stunning Railway Museum in

Check out this attractive fellowship call (health-life-sciences.de/postdocs) and especially the collaborative project (No. 51) from our lab and that of Aurelio Teleman on the evolution of X chromosome dosage compensation through translational upregulation in mammals!

P.S. this is one of our last posts here – follow us to where the sky is blue!

So excited to announce that our study on the development and evolution of pallial cell types and structures in birds led by Bassi Zaremba is now out in Science Magazine! science.org/doi/10.1126/sc… PS: this is our last post here – please follow us to where the sky is blue!

We all know quantization works at inference time, but researchers successfully trained a 13B LLaMA 2 model using FP4 precision (only 16 values per weight!). 🤯 We break down how it works. If quantization and mixed-precision training sounds mysterious, this’ll clear it up. See

Say hi if you're at ICLR! 👋

Long videos are a nightmare for language models—too many tokens, slow inference. ☠️ We explain STORM ⛈️, a new architecture that improves long video LLMs using Mamba layers and token compression. Reaches better accuracy than GPT-4o on benchmarks and up to 8× more efficiency.👇

Excited to share that I’ll be joining the Summer School “AI and Human Values” this September at the Marsilius-Kolleg of Heidelberg University as a speaker. I'll be giving an introduction to how large language models actually work—before the summer school dives deeper into their

💡 AlphaEvolve is a new AI system that doesn’t just write code, it evolves it. It uses LLMs and evolutionary search to make scientific discoveries. We explain how AlphaEvolve works and the evolutionary strategies behind it (like MAP-Elites and island-based population methods).

📺 youtu.be/Z4uF6cVly8o

We train AI on human-selected or -generated data (yes, even taking a photo is concept selection – we capture what we find interesting; text even more so, expressing our conceptualisation of the world). Then we’re surprised when the AI's concepts and representations are similar to

🧠🤖 Can we trust AI in science? I'm excited to be speaking at the final event of the Young Marsilius Fellows 2025, themed "Dancing with Right & Wrong?" – a title that feels increasingly relevant in the age of AI. I'll be joining a panel on "(How) can we trust AI in science?" to

Excited to be at #ACL2025NLP in Vienna this week. 🇦🇹 I’m always up for a chat about reasoning models, NLE faithfulness, synthetic data generation, or the joys and challenges of explaining AI on YouTube. If you're around, let’s connect!

How do LLMs pick the next word? They don’t choose words directly: they only output word probabilities. 📊 Greedy decoding, top-k, top-p, min-p are methods that turn these probabilities into actual text. In this video, we break down each method and show how the same model can

My friend Vivi Nastase is working on a short science communication film called "Puppets of a Digital Brain". It aims to explain the tech behind AI chatbots (the good, the bad, the environmental) in an accessible, visual way. Check it out if you’re curious or feel like supporting

The world’s largest NLP conference with almost 2,000 papers presented, ACL 2025 just took place in Vienna! 🎓✨Here is a quick snapshot of the event via a short interview with one of the authors whose work caught my attention. 🎥 Watch: youtu.be/GBISWggsQOA #acl2025NLP

Ever wondered how Energy-Based Models (EBMs) work and how they differ from normal neural networks? ☕️We go over EBMs and then dive into the Energy-Based Transformers paper to make LLMs that refine guesses, self-verify, and could adapt compute to problem difficulty. (link👇)