LEGO-OPD: Factorized Teacher Composition for Multimodal On-Policy Distillation

arXiv:2610.00333 · cs.CV, cs.AI, cs.CL, cs.LG · Submitted 2026-09-29 · Read on arXiv

cs.CV, cs.AI, cs.CL, cs.LG

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Grounding — 81× in this paper · explained in 3 episodes
• Calibration — 70× in this paper · explained in 7 episodes
• Benchmark — 56× in this paper · explained in 2 episodes
• Distillation — 44× in this paper · explained in 2 episodes
• Multimodal Reasoning — 23× in this paper · explained in 5 episodes
• On-Policy Distillation — 16× in this paper · explained in 3 episodes
• Visual Grounding — 12× in this paper · explained in 2 episodes
• Accuracy — 10× in this paper · explained in 1 episode
• Ablation — 6× in this paper · explained in 1 episode
• Alignment — 4× in this paper · explained in 1 episode
• Foundation Model — 3× in this paper · explained in 3 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• Generative AI — 3× in this paper · explained in 2 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Hallucination — 2× in this paper · explained in 3 episodes
• Self-Distillation — 2× in this paper · explained in 7 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 1× in this paper
• Decoupling — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes

Sources

• Qwen3-VL Technical Report
• Visual Contrastive Self-Distillation
• MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
• Visual-Advantage On-Policy Distillation for Vision-Language Models
• MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
• Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation
• Qwen3 Technical Report
• H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation

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