From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World Paper • 2605.10834 • Published 9 days ago • 6
Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning Paper • 2606.01682 • Published Jun 1 • 7
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published May 7 • 238