Adaptive Multi-Agent AI for Reliable Self-Harm Risk Screening
Discover how adaptive multi-agent AI systems improve reliability in self-harm risk screening with enhanced precision and reduced errors.
AI Bias in Advice: Individualism vs Collectivism Across Cultures
Study reveals AI favors individualist values over collectivist ones, impacting advice relevance across cultures. Explore cultural bias in large language mo...
PermaFrost-Attack: Stealth Logic Landmines in LLM Training
Discover how PermaFrost-Attack uses Stealth Pretraining Seeding to embed hidden logic landmines in LLMs, posing new AI security risks.
Spontaneous Persuasion by AI: How LLMs Influence Daily Talks
Discover how large language models use spontaneous persuasion in everyday chats, outperforming humans with data-driven, subtle influence techniques.
Wiggle and Go! Zero-Shot Dynamic Rope Manipulation
Discover Wiggle and Go! framework for zero-shot dynamic rope manipulation, boosting robotic precision with system identification and action prediction.