OC-OPD: Observation-coordinated Supervision for On-Policy Distillation
cs.LG, cs.AI, math.OC
Submitted: 2026-11-01
Updated: 2026-11-01
Code: https://github.com/RuoranXu/OC-OPD
Terminology
Sources
- Distilling the Knowledge in a Neural Network
- On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- Scaling Reasoning Efficiently via Relaxed On-Policy Distillation
- Entropy-Aware On-Policy Distillation of Language Models
- SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision
- TIP: Token Importance in On-Policy Distillation
- Mismatch Matters: On-Policy Distillation Beyond Token Agreement
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
- Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
- Stable On-Policy Distillation through Adaptive Target Reformulation
- PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation
- Trust Region On-Policy Distillation
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- Let's Verify Step by Step
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis