Ahmed Sharshar

Adversarial training on Fourier phase perturbations unlocks over 20% domain generalization gains in medical imaging by decoupling spatial structure from domain-specific textures.

Amnesia reveals that controlling replay indices can stealthily degrade continual learning models while remaining largely undetected by standard audit mechanisms.

Current AI safety filters can't tell a joke from a threat, especially when humor relies on cultural context – this new benchmark exposes that blind spot.

Forget static captions, ChatENV lets you chat with satellite images and sensor data to simulate environmental scenarios.