Insightful read #PaperILike from this week: Learning in Low-Dimensional Subspaces: Orthogonal Bottlenecks for Reinforcement [Aleksandar Todorov and Matthia Sabatelli] rlj.cs.umass.edu/2026/papers/...

Show Post

📢 New @neuripsconf.bsky.social paper with @jan-peters.bsky.social & @olegarenz.bsky.social : "A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning" We show that natural-gradient reward updates in inverse RL require no Fisher matrix at all 🧵👇

Show Post

The "controversial" comic with over 43 false reports to silence the creator and the real feel of the people. Enjoy, like and reshare "The Day All Billionaires Died..." By #noneofthisisok

Show Post

Today we are announcing a new partnership between @kesai.eu and @valeoai.bsky.social aimed at building generalist autonomous driving systems. We will open-source all results of this collaboration! kesai.eu/blog/2026-10...

Show Post

OpenAI’s faster Fourier transform is less a mathematical breakthrough and more a malicious exploit of mathematical traditions.

Show Post