# Learning Domain Knowledge in Multimodal Large Language Models through Reinforcement Fine-Tuning

arXiv: https://arxiv.org/abs/2601.16419 · HTML: https://mlsanity.com/paper/2601.16419/

## Key facts

- Cited by 1 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 38 of its 44 references that are in the map.
- First posted on arXiv 23 Jan 2026.

## Placed in

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

## Builds on (most cited first, 30 of 38)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification](https://mlsanity.com/paper/1608.05167/) (2016)
- [Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark](https://mlsanity.com/paper/1909.00133/) (2019)
- [R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization](https://mlsanity.com/paper/2503.12937/) (2025)
- [How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition](https://mlsanity.com/paper/2310.05492/) (2023)
- [Exploring Models and Data for Remote Sensing Image Caption Generation](https://mlsanity.com/paper/1712.07835/) (2017)
- [SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models](https://mlsanity.com/paper/2312.06739/) (2023)
- [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)
- [RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback](https://mlsanity.com/paper/2402.03681/) (2024)
- [Ovis2.5 Technical Report](https://mlsanity.com/paper/2508.11737/) (2025)
- [Contextual Object Detection with Multimodal Large Language Models](https://mlsanity.com/paper/2305.18279/) (2023)
- [PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval](https://mlsanity.com/paper/1706.03424/) (2017)
- [Group Robust Preference Optimization in Reward-free RLHF](https://mlsanity.com/paper/2405.20304/) (2024)
- [Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback](https://mlsanity.com/paper/2506.03106/) (2025)
- [Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation](https://mlsanity.com/paper/2402.10210/) (2024)
- [Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training](https://mlsanity.com/paper/2410.08202/) (2024)
- [Large-scale Reinforcement Learning for Diffusion Models](https://mlsanity.com/paper/2401.12244/) (2024)
- [REBEL: Reinforcement Learning via Regressing Relative Rewards](https://mlsanity.com/paper/2404.16767/) (2024)
- [Q-VLM: Post-training Quantization for Large Vision-Language Models](https://mlsanity.com/paper/2410.08119/) (2024)
- [MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2409.05840/) (2024)

## Built on by (most cited first, 1 of 1)

- [Large language models for partial differential equation workflows](https://mlsanity.com/paper/2608.03600/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) have shown remarkable capabilities in multimodal perception and understanding tasks. However, their effectiveness in specialized domains, such as remote sensing and medical imaging, remains limited. A natural approach to domain adaptation is to inject domain knowledge through textual instructions, prompts, or auxiliary captions. Surprisingly, we find that such input-level domain knowledge injection yields little to no improvement on scientific multimodal tasks, even when the domain knowledge is explicitly provided. This observation suggests that current MLLMs fail to internalize domain-specific priors through language alone, and that domain knowledge must be integrated at the optimization level. Motivated by this insight, we propose a reinforcement fine-tuning framework that incorporates domain knowledge directly into the learning objective. Instead of treating domain knowledge as descriptive information, we encode it as domain-informed constraints and reward signals, shaping the model's behavior in the output space. Extensive experiments across multiple datasets in remote sensing and medical domains consistently demonstrate good performance gains, achieving state-of-the-art results on multimodal domain tasks. Our results highlight the necessity of optimization-level domain knowledge integration and reveal a fundamental limitation of textual domain conditioning in current MLLMs.