PMOPD: Task Ordering, Cycling, and Parameter-Update Subspace Protection in Multi-Teacher On-Policy Distillation

arXiv:2609.34605 · cs.LG · Submitted 2026-09-28 · Read on arXiv

cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Distillation — 1× in this paper · explained in 2 episodes
• On-Policy Distillation — 1× in this paper · explained in 3 episodes

Sources

• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• The Llama 3 Herd of Models
• Distilling the Knowledge in a Neural Network
• Kimi K3: Open Frontier Intelligence
• Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
• MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
• Qwen2.5 Technical Report
• Policy Distillation
• On the Geometry of On-Policy Distillation
• MiMo-V2-Flash Technical Report

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