Hi, I'm Chris Wendler!

I am a postdoc in the interpretable neural networks lab at Northeastern University. My research focus is on deep learning 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.