Hi, I'm Chris Wendler!

I am a research scientist at world labs, where I train world models.

Before that I was a postdoc in the interpretable neural networks lab at Northeastern University. Before that I did another wonderful postdoc with the data science and AI laboratory and a Dr. sc. at ETH Zurich with the advanced computing laboratory. My research focus is on deep learning, world models and mechanistic interpretability. Check out our recent work on diffusion models.

Play pong inside of a small frame-autoregressive transformer trained with rectified flow matching. Please ping me if you want to try this while it is offline. It is currently not robustly hosted.

Please feel free to get in touch! You can send me an anonymous message here or contact me via email.