Calibrating Teacher--Student Discrepancy for On-Policy Distillation
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
Coupled Calibration and Learning: Mitigating Teacher Bias in LLM Distillation without Target-Domain Reward Feedback
1
Sakana AI Researchers Introduce PC-ALM, a Layer-Local Alternative to Backpropagation That Trains 1000-Layer Networks
4 min2
Negative Self-Distillation: Learning to Reason by Avoiding Flaws
1
Kalman Delta Networks: Uncertainty-aware Associative Memory
