Seonglae Cho

seonglae's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 9 days ago

FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies

Paper • 2506.17673 • Published 12 days ago • 6

authored a paper 10 days ago

LibVulnWatch: A Deep Assessment Agent System and Leaderboard for Uncovering Hidden Vulnerabilities in Open-Source AI Libraries

Paper • 2505.08842 • Published May 13

authored a paper over 1 year ago

RTSUM: Relation Triple-based Interpretable Summarization with Multi-level Salience Visualization

Paper • 2310.13895 • Published Oct 21, 2023