paper-with-me

홈 › Papers

BaseReward: A Strong Baseline for Multimodal Reward Model

2025-09-19 · Yi-Fan Zhang, Haihua Yang, Huanyu Zhang, Yang Shi, Zezhou Chen, Haochen Tian, Chaoyou Fu, Haotian Wang, Kai Wu, Bo Cui, Xu Wang, Jianfei Pan, Haotian Wang, Zhang Zhang, Liang Wang arxiv

The rapid advancement of Multimodal Large Language Models (MLLMs) has made aligning them with human preferences a critical challenge. Reward Models (RMs) are a core technology for achieving this goal, but a systematic guide for building state-of-the-art Multimodal Reward Models (MRMs) is currently lacking in both academia and industry. Through exhaustive experimental analysis, this paper aims to provide a clear ``recipe'' for constructing high-performance MRMs. We systematically investigate every crucial component in the MRM development pipeline, including \textit{reward modeling paradigms} (e.g., Naive-RM, Critic-based RM, and Generative RM), \textit{reward head architecture}, \textit{training strategies}, \textit{data curation} (covering over ten multimodal and text-only preference datasets), \textit{backbone model} and \textit{model scale}, and \textit{ensemble methods}. Based on these experimental insights, we introduce \textbf{BaseReward}, a powerful and efficient baseline for multimodal reward modeling. BaseReward adopts a simple yet effective architecture, built upon a {Qwen2.5-VL} backbone, featuring an optimized two-layer reward head, and is trained on a carefully curated mixture of high-quality multimodal and text-only preference data. Our results show that BaseReward establishes a new SOTA on major benchmarks such as MM-RLHF-Reward Bench, VL-Reward Bench, and Multimodal Reward Bench, outperforming previous models. Furthermore, to validate its practical utility beyond static benchmarks, we integrate BaseReward into a real-world reinforcement learning pipeline, successfully enhancing an MLLM's performance across various perception, reasoning, and conversational tasks. This work not only delivers a top-tier MRM but, more importantly, provides the community with a clear, empirically-backed guide for developing robust reward models for the next generation of MLLMs.

📄 PDF Abstract BibTeX arXiv:2509.16127

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation

2026-07-07 · Zhengbo Jiao, Yiming Cheng, Yilei Jiang, Kaituo Feng 외 arxiv

Training multimodal search agents to perform multi-hop reasoning remains challenging due to a fundamental structural disconnect: existing pipelines construct training data, search environments, and reward signals indepen…

BLM-Guard: Explainable Multimodal Ad Moderation with Chain-of-Thought and Policy-Aligned Rewards

2026-02-20 · Yiran Yang, Zhaowei Liu, Yuan Yuan, Yukun Song 외 arxiv

Short-video platforms now host vast multimodal ads whose deceptive visuals, speech and subtitles demand finer-grained, policy-driven moderation than community safety filters. We present BLM-Guard, a content-audit framewo…

Reinforcement Learning

MediX-R1: Open Ended Medical Reinforcement Learning

2026-02-26 · Sahal Shaji Mullappilly, Mohammed Irfan Kurpath, Omair Mohamed, Mohamed Zidan 외 arxiv

We introduce MediX-R1, an open-ended Reinforcement Learning (RL) framework for medical multimodal large language models (MLLMs) that enables clinically grounded, free-form answers beyond multiple-choice formats. MediX-R1…

Reinforcement Learning

Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image

2025-12-18 · Yushi Hu, Reyhane Askari-Hemmat, Melissa Hall, Emily Dinan 외 arxiv

Reward models (RMs) are essential for training large language models (LLMs), but remain underexplored for omni models that handle interleaved image and text sequences. We introduce Multimodal RewardBench 2 (MMRB2), the f…

Multimodal ReasoningImage Editing

Endogenous Reprompting: Self-Evolving Cognitive Alignment for Unified Multimodal Models

2026-01-28 · Zhenchen Tang, Songlin Yang, Zichuan Wang, Bo Peng 외 arxiv

Unified Multimodal Models (UMMs) exhibit strong understanding, yet this capability often fails to effectively guide generation. We identify this as a Cognitive Gap: the model lacks the understanding of how to enhance its…

Reinforcement Learning