# DT2IT-MRM: Debiased Preference Construction and Iterative Training for Multimodal Reward Modeling

arXiv: https://arxiv.org/abs/2604.19544 · HTML: https://mlsanity.com/paper/2604.19544/

## Key facts

- No citing papers in the map yet (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 23 of its 67 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 23 of 23)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning](https://mlsanity.com/paper/2503.07365/) (2025)
- [Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization](https://mlsanity.com/paper/2411.10442/) (2024)
- [Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy](https://mlsanity.com/paper/2507.01352/) (2025)
- [G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model](https://mlsanity.com/paper/2312.11370/) (2023)
- [Unified Reward Model for Multimodal Understanding and Generation](https://mlsanity.com/paper/2503.05236/) (2025)
- [Aligning Modalities in Vision Large Language Models via Preference Fine-tuning](https://mlsanity.com/paper/2402.11411/) (2024)
- [Secrets of RLHF in Large Language Models Part II: Reward Modeling](https://mlsanity.com/paper/2401.06080/) (2024)
- [VisualPRM: An Effective Process Reward Model for Multimodal Reasoning](https://mlsanity.com/paper/2503.10291/) (2025)
- [R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning](https://mlsanity.com/paper/2505.02835/) (2025)
- [Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models](https://mlsanity.com/paper/2502.14191/) (2025)
- [LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model](https://mlsanity.com/paper/2509.00676/) (2025)
- [Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning](https://mlsanity.com/paper/2505.07263/) (2025)
- [Evaluating MLLMs with Multimodal Multi-image Reasoning Benchmark](https://mlsanity.com/paper/2506.04280/) (2025)
- [BaseReward: A Strong Baseline for Multimodal Reward Model](https://mlsanity.com/paper/2509.16127/) (2025)
- [Generative RLHF-V: Learning Principles from Multi-modal Human Preference](https://mlsanity.com/paper/2505.18531/) (2025)
- [Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences](https://mlsanity.com/paper/2510.23451/) (2025)

## Abstract (arXiv)

Multimodal reward models (MRMs) play a crucial role in aligning Multimodal Large Language Models (MLLMs) with human preferences. Training a good MRM requires high-quality multimodal preference data. However, existing preference datasets face three key challenges: lack of granularity in preference strength, textual style bias, and unreliable preference signals. Besides, existing open-source multimodal preference datasets suffer from substantial noise, yet there is a lack of effective and scalable curation methods to enhance their quality. To address these limitations, we propose DT2IT-MRM, which integrates a Debiased preference construction pipeline, a novel reformulation of text-to-image (T2I) preference data, and an Iterative Training framework that curates existing multimodal preference datasets for Multimodal Reward Modeling. Our experimental results show that DT2IT-MRM achieves new state-of-the-art overall performance on three major benchmarks: VL-RewardBench, Multimodal RewardBench, and MM-RLHF-RewardBench.