A standalone fork of Zed's GPUI framework reworks the layout engine to retain unchanged work between frames, cutting main-thread frame times by up to 55 percent.
A new framework from Georgia Tech uses Bayesian uncertainty to tell SAM exactly where to ask for its next click, beating human annotators on 14 of 16 datasets.
An EPFL team gave frontier LLMs trained EEG and ECG network weights as text and asked them to debug, repair, and even write networks from scratch, without any gradient descent.