VisCoder2: Advanced Multi-Language Visualization Coding Agent
Discover VisCoder2, a cutting-edge multi-language visualization coding agent with 82.4% execution accuracy and robust self-debugging capabilities.
Contrastive Decoding Reduces Score Bias in LLM Evaluations
Learn how contrastive decoding improves Large Language Models' scoring accuracy by reducing score range bias, boosting reliability in LLM evaluations by 11...
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.
Wireless Sensor Networks for Real-Time Industrial Control
Discover how wireless sensor networks enable real-time monitoring and remote control of industrial environments for enhanced safety and efficiency.
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.