Tag: Vision-Language Models
Browse our exclusive articles!
SocraticAgent Boosts VLMs for Remote Sensing Images
Discover how SocraticAgent and RS-EoT improve vision-language models for accurate remote sensing image analysis and reasoning.
SAVANT: Enhancing Semantic Anomaly Detection with VLMs
Discover how SAVANT uses VLMs and structured reasoning to boost semantic anomaly detection in autonomous driving by 18.5% recall improvement.
Stealthy Jailbreak Attacks on Mobile Vision-Language Agents
Discover how stealthy jailbreak attacks exploit vulnerabilities in mobile vision-language agents, highlighting urgent security needs for AI systems.
Perception-Grounded Policy Optimization for Vision-Language Models
Improve Large Vision-Language Models with Perception-Grounded Policy Optimization that enhances token-level learning for better multimodal reasoning.
KITE: Efficient Robot Failure Analysis with VLMs
Discover KITE, a training-free system using keyframe tokenization and bird's-eye-view for advanced robot failure analysis with vision-language models.