arxiv:2605.19147
John Halloran
johnhalloran
AI & ML interests
None yet
Recent Activity
commentedon a paper about 3 hours ago
MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference Alignment commentedon a paper about 3 hours ago
Leveraging RAG for Training-Free Alignment of LLMs updated a dataset about 14 hours ago
johnhalloran/mcp-fbasOrganizations
None yet
