Slow-Fast Multi-Teacher On-Policy Distillation for Capability Preservation

arXiv:2610.02324 · cs.LG, cs.AI · Submitted 2026-10-01 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-10-01

Updated: 2026-10-01

Terminology

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

Sources

• Qwen3-VL Technical Report
• MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation
• OPD-V: Visual On-Policy Self-Distillation with Modality Balance
• DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning
• Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
• Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
• Group Sequence Policy Optimization

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