It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs Paper • 2605.20258 • Published May 18 • 30
Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR Paper • 2605.15726 • Published May 15 • 36
THINKSAFE: Self-Generated Safety Alignment for Reasoning Models Paper • 2601.23143 • Published Jan 30 • 39
Rethinking Reward Models for Multi-Domain Test-Time Scaling Paper • 2510.00492 • Published Oct 1, 2025 • 28
FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA Paper • 2505.12805 • Published May 19, 2025 • 22
FedRand: Enhancing Privacy in Federated Learning with Randomized LoRA Subparameter Updates Paper • 2503.07216 • Published Mar 10, 2025 • 32
