Trivial Trojans: How Minimal MCP Servers Enable Cross-Tool Exfiltration of Sensitive Data1просмотр4 месяца назад
CoT-Self-Instruct: Building High-Quality Synthetic Prompts for Reasoning and Non-Reasoning Tasks5просмотров4 месяца назад
Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Gene6просмотров5 месяцев назад
Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition2просмотра5 месяцев назад
Conferences for Multi-Agent Systems Applications: Submission Opportunities the end 20254просмотра5 месяцев назад
Subliminal Learning: Language models transmit behavioral traits via hidden signals in data2просмотра5 месяцев назад
