CatBarks/pi-c0-c8-technique-dataset-clean_harmful_only_with_benign_tech2_self_reminder_v5 Viewer • Updated 24 days ago • 2.66k • 75 • 1
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published May 12 • 196
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution Paper • 2605.18401 • Published May 18 • 131
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper • 2605.12882 • Published May 13 • 274