How would you evaluate a new causal discovery method? A new paper by Brouillard et al. challenges the common approaches and suggests a rethink. Here’s what they found 🧵👇 arxiv.org/abs/2412.01953 #CausalSky

My first post here :) Excellent news from NeurIPS. Two papers in, including a spotlight. 1. Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe 2. Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control

I have created a starter pack for the Polish ML community. Let's grow it together! Let me know if you know somebody who should be included. go.bsky.app/TSkgFjK

Here is an interesting starter pack with ELLIS researchers go.bsky.app/Cihupkk