Excited to share our preprint on our new multi-omic atlas of human hindbrain development. Led by postdoc Piyush Joshi, in collaboration with @kaessmannlab.bsky.social and Pfister labs, our atlas represents the first comprehensive view of human hindbrain development. www.biorxiv.org/content/10.6...

Computerlinguistin und Geoinformatiker mit „KlarText-Preis“ ausgezeichnet – Hervorragende Wissenschaftskommunikation: Letitia Parcalabescu und Steffen Knoblauch präsentieren Ergebnisse ihrer Doktorarbeiten in allgemeinverständlicher Form www.uni-heidelberg.de/de/newsroom/... #wisskomm

LLMs can memorize even a phone number seen once in training.🔒 Google’s VaultGemma fixes that, being the first open-weight LLM trained from scratch with differential privacy, so rare secrets leave no trace. ☕ new video explaining Differential Privacy through VaultGemma 👇 🎥 youtu.be/UwX5zzjwb_g

What's up with Google's new VaultGemma model? – Differential Privacy explained

YouTube video by AI Coffee Break with Letitia

youtu.be

We explain diffusion models and flow-matching models side by side. Flow-Matching models are the new generation of AI image generators that are quickly replacing diffusion models. They take everything diffusion did well, but make it faster, smoother, and deterministic. 🎥 youtu.be/firXjwZ_6KI

Diffusion Models and Flow-Matching explained side by side

YouTube video by AI Coffee Break with Letitia

youtu.be

Did transposable elements shape brain evolution — and if so, which ones, and in which cell states and lineages? Led by @tyamadat.bsky.social, we explored this question in cerebellum development using sequence-based deep learning models! www.biorxiv.org/content/10.1...

We are thrilled to share our new preprint entitled “The origin and molecular evolution of the mammalian liver cell architecture” www.biorxiv.org/content/10.1...

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.

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

👇 !!!

Louis-Jeantet Foundation@louisjeantetfdn.bsky.social · 11mo ago

Register to attend the #LouisJeantetSymposium on vertebrate genome #evolution. Organised by Svante Pääbo and @kaessmannlab.bsky.social . Free event, full line up of speakers 👉 www.jeantet.ch/en/ 📆Tuesday 14 October, 08h15 📍CMU - Auditoire Alex-F. Müller (A250) @genevunige.bsky.social

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.

Excited to be at ACL 2025 in Vienna this week 🇦🇹 #ACL2025 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!

Our study on a male-essential microRNA and the evolution of other dosage compensation mechanisms in birds is now out in Nature! www.nature.com/articles/s41...

A male-essential miRNA is key for avian sex chromosome dosage compensation - Nature

Birds have evolved a unique sex chromosome dosage compensation mechanism involving the male-biased microRNA (miR-2954), which is essential for male survival by regulating the expression of dosage-sens...

nature.com

📅 Looking forward to the discussion and to learning from fellow panelists and participants. If you're around Heidelberg, join us! www.marsilius-kolleg.uni-heidelberg.de/de/dancing-w...

🤖 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 these days. I'll be joining a panel on "(How) can we trust AI in science?" to discuss questions like:

I'm very excited to finally share the main work of my PhD! We explored the evolutionary dynamics of gene regulation and expression during gonad development in primates. We cover among others: X chromosome dynamics (incl. in a developing XXY testis), gene regulatory networks and cell type evolution.

Kaessmann Lab@kaessmannlab.bsky.social · last yr.

We are delighted to share our new preprint “The evolution of gene regulatory programs controlling gonadal development in primates” www.biorxiv.org/content/10.1...

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 broader implications.

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. 📺 youtu.be/uMk3VN4S8TQ

Token-Efficient Long Video Understanding for Multimodal LLMs | Paper explained

YouTube video by AI Coffee Break with Letitia

youtu.be

🎯

A great article highlighting the broader implications of the three parallel recent papers from our group and our wonderful colleagues in Spain and Belgium...

Quanta Magazine@quantamagazine.org · last yr.

Calling someone bird-brained is, in fact, a way of calling someone highly intelligent. @yaseminsaplakoglu.bsky.social reports: www.quantamagazine.org/intelligence...

Just say “Wait…” – and your LLM gets smarter?! We explain how just 1,000 training examples + a tiny trick at inference time = o1-preview level reasoning. No RL, no massive data needed. 🎥 Watch now → youtu.be/XuH2QTAC5yI

s1: Simple test-time scaling: Just “wait…” + 1,000 training examples? | PAPER EXPLAINED

YouTube video by AI Coffee Break with Letitia

youtu.be

How does gene regulation shape brain evolution? Our new preprint dives into this question in the context of mammalian cerebellum development! rb.gy/dbcxjz Led by @ioansarr.bsky.social, @marisepp.bsky.social and @tyamadat.bsky.social, in collaboration with @steinaerts.bsky.social

So excited to announce that our study on the development and evolution of pallial cell types and structures in birds, led by @bassi-z.bsky.social, is now out in @science.org! www.science.org/doi/10.1126/...

Developmental origins and evolution of pallial cell types and structures in birds

Innovations in the pallium likely facilitated the evolution of advanced cognitive abilities in birds. We therefore scrutinized its cellular composition and evolution using cell type atlases from chick...

science.org

An educational and a bit historical deep dive into LLM research. 💡Learn what breakthroughs since 2017 paved the way for AI like ChatGPT (it wasn't overnight). We go through: * Transformers * Prompting * Human Feedback, etc. and break it all down for you! 👇 📺 youtu.be/BprirYymXrg

LLMs Explained: A Deep Dive into Transformers, Prompts, and Human Feedback

YouTube video by AI Coffee Break with Letitia

youtu.be

New video about: REPA (Representation Alignment), a clever trick to align diffusion transformers’ representations with pretrained transformers like DINOv2. It accelerates training and improves the diff. model’s ability to do things other than image generation (like image classification).

REPA Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You ...

YouTube video by AI Coffee Break with Letitia

youtu.be