yoon

sangyon's activity

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

authored a paper about 9 hours ago

Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures

Paper • 2602.03379 • Published Feb 3

authored a paper 4 days ago

BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs

Paper • 2603.16557 • Published 6 days ago • 20

authored 3 papers 2 months ago

SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment

Paper • 2505.14667 • Published May 20, 2025 • 12

R-TOFU: Unlearning in Large Reasoning Models

Paper • 2505.15214 • Published May 21, 2025 • 12

K-EXAONE Technical Report

Paper • 2601.01739 • Published Jan 5 • 93