John Halloran
johnhalloran
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
Leveraging RAG for Training-Free Alignment of LLMs authored a paper 1 day ago
MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference Alignment commentedon a paper 2 days ago
MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference AlignmentOrganizations
None yet