When Less is Enough: Adaptive Token Reduction for Efficient Image Representation Paper • 2503.16660 • Published Mar 20 • 73
Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders Paper • 2503.03601 • Published Mar 5 • 230
GHOST 2.0: generative high-fidelity one shot transfer of heads Paper • 2502.18417 • Published Feb 25 • 67