Tag
This paper develops a framework to study how linear concept representations emerge during neural network training, providing exact solutions in linear networks and analyzing abstraction dynamics in nonlinear networks. The results reveal key principles governing abstraction and offer implications for interpretability and control.
A web-based interactive simulator for crank-angle-resolved combustion engine dynamics, providing educational and engineering insights into engine behavior.
The article explains how the loudness war, typically a digital phenomenon, degrades vinyl record quality when compressed digital masters are used for vinyl cutting, using Prince's Purple Rain as an example.
This paper studies multilingual unlearning in LLMs by extending the TOFU benchmark to five languages. It finds that unlearning transfer varies by script and family, operates primarily in later decoding layers, and that a single steering direction can recover much of the suppressed knowledge across languages.
This paper presents a closed-form upper bound for admissible learning-rate steps in belief-space dynamics, providing a theoretical result for optimization in robotics or control.