Outcome-Guided On-Policy Self-Distillation
cs.LG
Submitted: 2026-10-04
Updated: 2026-10-04
Terminology
Sources
- Qwen3-VL Technical Report
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- OpenAI o1 System Card
- Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
- Scaling Reasoning Efficiently via Relaxed On-Policy Distillation
- When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
- AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Purified OPSD: On-Policy Self-Distillation Without Losing How to Think
- Kimi K3: Open Frontier Intelligence
- Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation
- On the Position Bias of On-Policy Distillation
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Qwen3 Technical Report
- Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning
- DOPD: Dual On-policy Distillation
- GLM-5: from Vibe Coding to Agentic Engineering
- Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning
- The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes
- Less is More: Early Stopping Rollout for On-Policy Distillation
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks