EasyProver solves near-saturated Lean benchmarks and half of harder Aegis tasks
On a stratified Aegis sample of 2,000 statements, it proves 1,054 within a 30-minute budget.
Stories per day · 30 days
1 RSS
2 stories, newest first · one card per story
Stories tagged #aegis
AEGIS: Audio Endogenous Guarding via Internal Signals Against Large Audio-Language Model Jailbreaks
AEGIS uses mid-layer risk signals to cut audio-model jailbreak unsafe rates from 17.9% to 0.4%.