The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer Paper • 2602.02557 • Published 7 days ago • 20
Forecasting Scientific Progress with Artificial Intelligence Paper • 2605.22681 • Published 15 days ago • 43
D^2-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Paper • 2605.25893 • Published 11 days ago • 39
Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation Paper • 2602.12125 • Published Feb 12 • 67