Robust and Calibrated Detection of Authentic Multimedia Content Paper • 2512.15182 • Published Dec 17, 2025 • 18
Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering Paper • 2610.05894 • Published Oct 5 • 14
Certification of Real Images through Calibrated Content Authentication Paper • 2610.05870 • Published Oct 5 • 12
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model Paper • 2610.08773 • Published Oct 6 • 11
Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision Paper • 2609.35718 • Published Sep 28 • 23