ConfigWM uses task language to filter distractors in world-model states
Authors report ConfigWM beats the strongest baseline by 22.3% on average as visual noise rises.
Stories per day · 30 days
4 stories, newest first · one card per story
Stories tagged #perception
FocusGUI adapter cuts sequential distraction in omni-modal GUI agents
Across four frozen backbones, authors report Type Match up 33.2 points and Exact Match 3.0 times the frozen baseline.
Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes
Where-OPD uses spatial self-distillation on synthetic scenes to improve multimodal perception.
Illusion of Depth: Revealing Hidden Stereo Vision Vulnerabilities in Depth Estimation
Simple repeating patterns let attackers shift stereo-camera depth estimates by up to 20 meters, triggering emergency braking in autonomous driving frameworks at 40 km/h.