PAST: Privileged Adaptation from Complete Student Trajectories for On-Policy Self-Distillation
Yangyang Feng, Zhuoyan Feng, Junlan Chen
cs.LG, cs.AI
Submitted: 2026-08-09
Updated: 2026-08-11
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- H$^2$SD: Hybrid Hindsight Self-Distillation
- Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance
- Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
- When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- PAINT: Partial-Solution Adaptive Interpolated Training for Self-Distilled Reasoners
- Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
- Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks