Progressive-View On-Policy Distillation for Regional-to-Global Transfer in Multimodal LLMs

arXiv:2609.32333 · cs.CV, cs.AI · Submitted 2026-09-26 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-26

Updated: 2026-09-26

Terminology

• Distillation — 25× in this paper · explained in 2 episodes
• Benchmark — 13× in this paper · explained in 2 episodes
• GRPO — 13× in this paper · explained in 6 episodes
• On-Policy Distillation — 9× in this paper · explained in 3 episodes
• Self-distillation — 5× in this paper · explained in 6 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Ablation — 3× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Exposure Bias — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Training-Free Framework — 1× in this paper · explained in 2 episodes

Sources

• Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
• On-Policy Self-Distillation without Any Supervision
• Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation
• Visual-Advantage On-Policy Distillation for Vision-Language Models
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Qwen3 Technical Report

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models