RS-OPSD: Reliable Privileged On-Policy-Self-Distillation for Ultra-High-Resolution Remote Sensing VQA

arXiv:2609.38072 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-30

Terminology

• Distillation — 25× in this paper · explained in 2 episodes
• Benchmark — 15× in this paper · explained in 2 episodes
• Accuracy — 13× in this paper · explained in 1 episode
• Self-distillation — 11× in this paper · explained in 6 episodes
• Pruning — 9× in this paper · explained in 4 episodes
• Regularization — 9× in this paper · explained in 3 episodes
• Correctness-Aligned Distillation — 5× in this paper
• Core — 4× in this paper · explained in 2 episodes
• KL Regularization — 4× in this paper · explained in 2 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• On-policy Self-Distillation (OPSD) — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Active Perception — 2× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Context-Preserving Visual Privilege — 2× in this paper
• LoRA Fine-Tuning — 2× in this paper · explained in 3 episodes
• On-Policy Distillation — 2× in this paper · explained in 3 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Route Planning — 2× in this paper
• Verification — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Annotation Errors — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Counting with Complex Reasoning — 1× in this paper
• Cross-Validation Acceptance Rate — 1× in this paper
• Environmental Conditional Reasoning — 1× in this paper
• Exponential Moving Average (EMA) — 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
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Object Motion State — 1× in this paper
• Object Spatial Relationship — 1× in this paper
• Overall Land Use Classification — 1× in this paper
• Regional Counting — 1× in this paper
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• LoRA: Low-Rank Adaptation of Large Language Models
• GPT-4o System Card
• LLaVA-OneVision: Easy Visual Task Transfer
• WeaveEarth: Structured Evidence Construction and Reasoning for Training-Free UHR Remote Sensing Understanding
• HybridFlow: A Flexible and Efficient RLHF Framework
• GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagery
• Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
• Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
• Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Search
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

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