11. A perfect model can still get causality backwards Frank Hutter, co-founder and CEO of Prior Labs, on why a model that predicts perfectly can still point you to the wrong decision. If patients who get a medicine tend to have a dise 09/24 02:09 ♡
12. The AI That Replaces Hours of Model Tuning - Frank Hutter Frank Hutter, co-founder of Prior Labs, talks about TabPFN, a tabular foundation model that makes predictions in a single forward pass, and the research behind it. TabPFN is pre-tr 09/24 02:06 ♡
13. A Perfect World Model of Chess Still Won't Beat Magnus Carlsen - Alexander Mattick Alexander Mattick (Fraunhofer IIS, UTN): a perfect world model of chess still will not beat Magnus Carlsen, because predicting the future and choosing the right action are differen 09/22 16:10 ♡
14. Why More Data Cannot Replace Prior Structure - Alexander Mattick Alexander Mattick is a researcher at Fraunhofer IIS and a PhD researcher at the University of Technology Nuremberg (UTN), and a regular on Yannic Kilcher's Discord. He first came o 09/21 23:09 ♡
15. How a Robot Tests an Action Before It Moves How can a robot test an action without moving? NVIDIA's Ming-Yu Liu explains how a world model predicts the outcome first. Cosmos 3 learns three abilities together: forward dynamic 09/16 00:09 ♡
