Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models Paper • 2610.10625 • Published 10 days ago • 1
Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models Paper • 2610.10623 • Published 10 days ago • 1
Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models Paper • 2610.10625 • Published 10 days ago • 1
Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models Paper • 2610.10623 • Published 10 days ago • 1
DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing Paper • 2502.11647 • Published May 29, 2025 • 1
EVA: Editing for Versatile Alignment against Jailbreaks Collection [IEEE TPAMI 2026] Official model checkpoints for EVA • 4 items • Updated Aug 26 • 2
DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing Paper • 2502.11647 • Published May 29, 2025 • 1
EVA: Editing for Versatile Alignment against Jailbreaks Collection [IEEE TPAMI 2026] Official model checkpoints for EVA • 4 items • Updated Aug 26 • 2
EVA: Editing for Versatile Alignment against Jailbreaks Collection [IEEE TPAMI 2026] Official model checkpoints for EVA • 4 items • Updated Aug 26 • 2