Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation

arXiv:2609.35347 · cs.LG · Submitted 2026-09-28 · Read on arXiv

cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/LiXin97/DN-MOPD

Project page: https://lixin.ai/DN-MOPD

Terminology

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

Sources

• On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
• GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
• Process Reinforcement through Implicit Rewards
• QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• MiniLLM: On-Policy Distillation of Large Language Models
• DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
• Measuring Mathematical Problem Solving With the MATH Dataset
• Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe
• Editing Models with Task Arithmetic
• LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
• Sequence-Level Knowledge Distillation
• Tulu 3: Pushing Frontiers in Open Language Model Post-Training
• CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation
• UI-MOPD: Multi-Platform On-Policy Distillation for Unified GUI Agents
• Let's Verify Step by Step
• Motif 3: 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