FILTERING PRETRAINING DATA BUILDS TAMPER-RESISTANT SAFEGUARDS INTO OPEN-WEIGHT LLMS3просмотра3 месяца назад
Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction2просмотра3 месяца назад
Recognising, Anticipating, and Mitigating LLM Pollution of Online Behavioural Research7просмотров3 месяца назад
Generative AI Adoption in Postsecondary Education, AI Hype, and ChatGPT’s Launch7просмотров3 месяца назад
Trivial Trojans: How Minimal MCP Servers Enable Cross-Tool Exfiltration of Sensitive Data1просмотр3 месяца назад
CoT-Self-Instruct: Building High-Quality Synthetic Prompts for Reasoning and Non-Reasoning Tasks5просмотров3 месяца назад
Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Gene6просмотров3 месяца назад
Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition2просмотра3 месяца назад
Conferences for Multi-Agent Systems Applications: Submission Opportunities the end 20253просмотра3 месяца назад
