Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders Paper • 2503.03601 • Published 9 days ago • 206
MLGym: A New Framework and Benchmark for Advancing AI Research Agents Paper • 2502.14499 • Published 22 days ago • 179
The Differences Between Direct Alignment Algorithms are a Blur Paper • 2502.01237 • Published Feb 3 • 112