FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies Paper • 2506.17673 • Published 13 days ago • 6
LibVulnWatch: A Deep Assessment Agent System and Leaderboard for Uncovering Hidden Vulnerabilities in Open-Source AI Libraries Paper • 2505.08842 • Published May 13
RTSUM: Relation Triple-based Interpretable Summarization with Multi-level Salience Visualization Paper • 2310.13895 • Published Oct 21, 2023