# Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation

arXiv: https://arxiv.org/abs/2605.18740 · HTML: https://mlsanity.com/paper/2605.18740/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 65 of its 74 references that are in the map.
- First posted on arXiv 18 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)
- Knowledge distillation / [Multimodal distillation](https://mlsanity.com/distill/multimodal-distillation/)

## Builds on (most cited first, 30 of 65)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [Are We on the Right Way for Evaluating Large Vision-Language Models?](https://mlsanity.com/paper/2403.20330/) (2024)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs](https://mlsanity.com/paper/2312.14135/) (2023)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models](https://mlsanity.com/paper/2601.18734/) (2026)
- [Policy Distillation](https://mlsanity.com/paper/1511.06295/) (2015)
- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025)
- [ShortGPT: Layers in Large Language Models are More Redundant Than You Expect](https://mlsanity.com/paper/2403.03853/) (2024)
- [Reinforcement Learning via Self-Distillation](https://mlsanity.com/paper/2601.20802/) (2026)
- [MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?](https://mlsanity.com/paper/2408.13257/) (2024)
- [Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning](https://mlsanity.com/paper/2505.15966/) (2025)
- [Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models](https://mlsanity.com/paper/2406.09403/) (2024)
- [MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe](https://mlsanity.com/paper/2509.18154/) (2025)
- [MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs](https://mlsanity.com/paper/2502.17422/) (2025)
- [Thyme: Think Beyond Images](https://mlsanity.com/paper/2508.11630/) (2025)
- [Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models](https://mlsanity.com/paper/2408.15556/) (2024)
- [Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing](https://mlsanity.com/paper/2506.09965/) (2025)

## Built on by (most cited first, 30 of 77)

- [Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning](https://mlsanity.com/paper/2606.18974/) (2026)
- [ViCuR: Visual Cues as Recoverable Privilege for Multimodal On-Policy Distillation](https://mlsanity.com/paper/2606.05718/) (2026)
- [DOPD: Dual On-policy Distillation](https://mlsanity.com/paper/2606.30626/) (2026)
- [Visual Contrastive Self-Distillation](https://mlsanity.com/paper/2607.21556/) (2026)
- [Thinking Without Images: Internalizing Visual Manipulation with On-Policy Self-Distillation](https://mlsanity.com/paper/2606.08719/) (2026)
- [H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation](https://mlsanity.com/paper/2607.02592/) (2026)
- [ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation](https://mlsanity.com/paper/2607.13124/) (2026)
- [Weak-to-Strong On-Policy Distillation](https://mlsanity.com/paper/2607.26246/) (2026)
- [OPD-V: Visual On-Policy Self-Distillation with Modality Balance](https://mlsanity.com/paper/2608.05131/) (2026)
- [VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation](https://mlsanity.com/paper/2607.28590/) (2026)
- [Latent On-Policy Self-Distillation](https://mlsanity.com/paper/2608.13040/) (2026)
- [SenseNova-U1.5: Towards Native Unified Visual Intelligence](https://mlsanity.com/paper/2609.11929/) (2026)
- [MAIGO: Mitigating Lost-in-Conversation with History-Cleaned On-Policy Self-Distillation](https://mlsanity.com/paper/2605.27186/) (2026)
- [ParaBridge: Bridging Paralinguistic Perception and Dialogue Behavior in Speech Language Models](https://mlsanity.com/paper/2606.10581/) (2026)
- [OmniOPSD: Rationale-Privileged On-Policy Self-Distillation for Affective Computing](https://mlsanity.com/paper/2606.15920/) (2026)
- [A Formula-Driven Survey and Research Agenda for On-Policy Distillation](https://mlsanity.com/paper/2606.22793/) (2026)
- [RP-OPSD: Resolution-Privileged On-Policy Self-Distillation for Multimodal Large Language Models](https://mlsanity.com/paper/2607.24447/) (2026)
- [Self-Supervised Visual On-Policy Distillation](https://mlsanity.com/paper/2608.14144/) (2026)
- [When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation](https://mlsanity.com/paper/2608.03632/) (2026)
- [Where to Look Matters: On-Policy Self-Distillation for Long-Video Understanding](https://mlsanity.com/paper/2608.25356/) (2026)
- [Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation](https://mlsanity.com/paper/2606.19120/) (2026)
- [Distill What the Student Can See: Fisher-Projected On-Policy Distillation for Vision-Language Models](https://mlsanity.com/paper/2608.01263/) (2026)
- [WAM-OPD: On-Policy Distillation for World Action Models](https://mlsanity.com/paper/2608.22364/) (2026)
- [Contrastive On-Policy Distillation](https://mlsanity.com/paper/2607.19046/) (2026)
- [Evidence-RL: Towards Evidence-intensive Visual Reasoning](https://mlsanity.com/paper/2608.08021/) (2026)
- [SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation](https://mlsanity.com/paper/2608.10775/) (2026)
- [Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation](https://mlsanity.com/paper/2606.06076/) (2026)
- [Med-OPD: Improving Medical Vision-Language Models via Evidence-Aware On-Policy Distillation](https://mlsanity.com/paper/2607.16303/) (2026)
- [Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection](https://mlsanity.com/paper/2607.27113/) (2026)
- [DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models](https://mlsanity.com/paper/2608.09233/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image. We observe a regional-to-global perception gap: the same MLLM answers fine-grained questions more accurately when conditioned on evidence-centered crops than on the corresponding full images, suggesting that many failures stem from difficulty to focus on relevant evidence rather than insufficient local recognition ability. Motivated by this observation, we propose Vision-OPD (Vision On-Policy Distillation), a regional-to-global self-distillation framework that transfers the model's own privileged regional perception to its full-image policy. Vision-OPD instantiates two conditional policies from the same MLLM: a crop-conditioned teacher and a full-image-conditioned student. The student generates on-policy rollouts, and Vision-OPD minimizes token-level divergence between the teacher and student next-token distributions along these rollouts. This enables the model to internalize the benefit of visual zooming without external teacher models, ground-truth labels, reward verifiers, or inference-time tool use. Experiments on multiple fine-grained visual understanding benchmarks show that Vision-OPD models achieve competitive or superior performance against much larger open-source, closed-source, and "Thinking-with-Images" agentic models. The code is available at https://github.com/VisionOPD/Vision-OPD